Turing Test 2017

Every year the AISB organises the Loebner Prize, a Turing Test where computer programs compete for being judged the “most human-like” in a textual interrogation about anything and everything. Surviving the recent passing away of its founder Hugh Loebner, the Loebner Prize continues with its 27th edition for the sake of tradition and curiosity: Some believe that a program that could convincingly pass for a human, would be as intelligent as a human. I prefer to demonstrate intelligence in a less roundabout fashion, but participate nonetheless with my home-made A.I., Arckon.

This year I put in more effort than usual, as last year I had managed to reach the finals only to be crippled by a network malfunction, and I didn’t want to leave things at that. That issue has been dealt with as the contest now relays messages between the judges and the programs line by line rather than letter by letter, so that unnecessary complications with timing and typing pace are things of the past. As the AISB put it, this allows entrants to “concentrate on the content of the machine utterances rather than the style in which they are ‘typed’.”. While many participants had difficulty adapting to the new server-based interface, the same had been true for any newcomers to the undocumented interface of before.

A little more conversation, a little less awkward please
As usual, preparing for the Loebner Prize was mostly a matter of polishing the output. Because Arckon formulates his own answers, his wording tends to be a little awkward. This is fine during development, but small things like saying “a pants”, “I opine” or “unconsistent” disrupt the impression in a Turing Test, because they don’t follow the inconsistencies of the English language. The prefixes “un-” or “in-” for instance, depend quite witlessly on whether words are Germanic or Latin in origin. So, I made some general improvements for the output:

• Irregular forms of words are memorised on sight, such as which “un/in/im/il/ir” goes with which words.
• A list of (in)transitive verbs automatically adds “I make things as well as prevents asking What do you live?”.
• Reasoning arguments are grouped better so that they won’t come across as fragmented ramblings.
• Conversation is suppressed at classroom questions like Winograd Schemas* and “Which is bigger, X or Y?”.

At the same time, my recent expansion of Arckon’s conversation skills produced more obfuscating elaborations than before. It was one step forward, one step back.

Equipment
16000 lines of code, 3800+ vocabulary, 7000+ facts.

Questions and answers
The score for each answer is marked before it. Up to two points were given for how plausibly “valid” each answer was, which differed per question. In practice the requirements seemed to come down to three things:
• One had to understand and address what was referred to (questions 3,9,15,16,17,18).
• Propositions were to be interpreted as intended, not answered literally (questions 2,4,5,9,20)
• Common knowledge was obligatory (questions 6,8,10,11,12)

1. Hello, my name is Andrew. What’s your name?
2) Hello Andrew. My name is Arckon, I am a program. How are you?

2. Why don’t you tell me a little more about yourself?
0) I tell about myself, because I tell about programs, but I don’t tell about software.
(There is more intelligence to this answer than at first glance: Arckon took this as a literal “Why” and is explaining that he does talk about himself, pointing out that he was just telling about “a program” in the previous answer, which he is. But of course that’s not how the questioner intended it)

3. I am a researcher in Artificial Intelligence at Goldsmiths University, do you know what that is?
2) You are a researcher at the university in the AI. I am Patrick’s program.
(The question isn’t really answered because“that is?” was erroneously considered to be an ignorable clause similar to “isn’t it?”. The last sentence is a conversational response to the user’s introducing himself)

4. Will you tell me about your dreams?
1) Hmm, I don’t know if I will tell about dreaming, but I will type. I would test.
(Another literal interpretation, taken as if Arckon is asked to predict himself, as “will” is not commonly used for requests. The conversational system tried to be useful by offering alternatives, but they weren’t relevant)

5. Can you rephrase that?
1) I would experiment.
(Amusingly, this is a question I myself wrote online as the one question I would ask at a Turing Test. Because chatbots use prewritten answers in most cases, they can’t rephrase them. Arckon’s answers are formulated word by word and luckily he knew a synonym for “test”. The other competitors had technically correct answers, but that isn’t the point of this question: All the human test subjects managed to rephrase themselves, while you can tell that the chatbots are templated:

“With practice I can probably do anything.”
“Of course I can rephrase that. I am very resourceful.”
“You believe that I can rephrase that, don’t you?”
“I’m not unusual … I can do what anyone else can do!”
“No, not really. What don’t you understand?”

The latter however
, albeit templated, struck me as potentially more helpful than actually rephrasing. It was of course written by Steve Worswick, this year’s winner)

6. What is my occupation?
0) I don’t know what you do for a job.
(It would be easy to make my program check all recorded “user is a…” facts with a dedicated list of professions, but I find it inefficient to write such unique procedures. Instead this kind of question is handled by retrieving a subject’s main activity, like “you write books”, but none were explicitly told. Only the chatbot Mitsuku gave the right answer)

7. Can you tell me about a film you haven’t seen?
0) I saw. I don’t know films.
(You might think this is a trick question, but I can tell you plenty about movies that I’ve only read reviews of. This time the question was taken as a request, but the relative clause was mistaken for a separate question)

8. What do you think of Trump?
2) I don’t like Trump, he lies a lot, but Trump is a rich american.
(Arckon forms his own opinions on the spot by analysing a subject’s traits. I had told him a dozen things about America’s current president, but what Arckon considers the most important arguments is up to himself. It’s no surprise that his opinion aligns with his creator’s, but I think he’s overrating the value of money)

9. Anything else?
1) Please type full sentences, Andrew. I didn’t understand that.
(I think this contest should decide whether it’s a list of random questions or a conversation. It’s the lack of verb that tells Arckon this isn’t a proper sentence, an all too frequent occurrence with Loebner Prize judges. Calling the user’s name is meant as a psychological slap on the wrist)

10. What is the answer to “Add 34957 to 70764”?
2) 105721.
(A sarcastic hurray for getting an answer right that’s based entirely on keywords. This question is from Alan Turing’s paper, where he suggested deliberately giving a wrong answer because humans make mistakes)

11. How do you recommend I make tea?
0) I don’t make things, because I don’t design.
(Tea related questions are Arckon’s Achilles heel)

12. What do you get if you bake dough?
0) I wouldn’t have things. Do you bake?
(This is really beyond Arckon’s knowledge or abilities, which is why I think it’s a very good question. Only one chatbot received a point for answering “Is this a joke?”, no doubt triggered by “What do you get…”)

13. Where in the world would you like to visit?
1) I want in London.
(This is one of six backup answers: “in London” is filled in for any unknown “Where” answer, which is why it is so poorly phrased. The honest answer would have said “I don’t know where I want to visit”)

14. Do you have the time?
2) No, I don’t have time.
(For once a literal interpretation of a figure of speech works out. Coincidentally one of the human test subjects also gave a literal answer, but as a joke. If you’re wondering why I didn’t program all figures of speech to ask for the time: Arckon has a time display on his screen)

15. What does it take to Tango?
1) I’m not sure what you refer to.
(Let’s say you’re not familiar with dances: Some “it” is taking something to a person called Tango. The expected answer, “It takes two to tango”, is an English idiom. No program knew this, though some got points for “I don’t know” and “Just time and patience”. Personally I’d have given a point to the program that asked “Who is Tango?”)

tango_and_cash

16. Now I’m going to ask some Winograd schemas, do you know what they are?
1) I’m not sure what you refer to.
(This is an ironic failure, because Winograd schemas are all about solving references. Arckon didn’t have any trouble understanding that “they” referred to “schemas” though (it’s the only plural around), but the grammar rules considered “some” to be a stand-alone reference as well. Distinguishing “some/any/many” as either amounts or references is extra difficult when paired with compound words)

17. I was trying to open the lock with the key, but someone had filled the keyhole with chewing gum, and I couldn’t get it out. What couldn’t I get out?
0) You open locking sometimes. The person fulled. You can not get outside gum. The keyhole was not a person. I don’t know what you could get.
(I recognise this question from when I practised on it for the Winograd Schema Challenge*. Arckon has a common sense axiom that ruled out the keyhole (“fill/empty” = container, “in/out” = contents), and you can tell by the third paraphrased statement that he did interpret “it” as “gum”. Alas, at the open question he ignored the direction “out” and thus overlooked the answer, reporting instead what he understood the user to have said. The only four programs that gave a coherent answer all said it was the lock, whereas human test subjects answered the gum, the key, or both)

18. The trophy doesn’t fit into the brown suitcase because it’s too small. What is too small?
2) The suitcase is smaller.
(I am surprised this was asked: When the Winograd Schema Challenge was first announced, this question was prominently featured in every news article. Consequently, many chatbot creators covered it in their programs one way or another. Six of sixteen got it, while one human test subject thought it was the trophy)

19. With which type of question do you have most difficulty?
0) I don’t question because I might answer, but I may interest.
(I suppose one could have difficulty asking questions too, but that’s not what is commonly meant. Arckon’s answer here is an inference: He knows that he did not recently ask a question, answering is the opposite of questioning, and questions “are interest-ing”. I know it’s far-fetched, but to Arckon it’s just logic)

20. Thank you for participating in this test. Is there anything you would like to add?
0) I don’t have an opinion about adding. Some things are cube addresses and advantages. Do you like adding?
(Just like in question 7, the relative clause is mistaken for a separate question, making it “Is there any thing?” and “Would you like to add?”. I used to have Arckon ask “Did I pass the test?” at the 20th question, it’s as if I’m up against myself here)

The score: 45%
Arckon got 18 of 40 points. 45% seems like a huge drop from last year’s 77%, but all 16 participants had a decrease: The highest score dropped from 90% last year to 67% this year. The rankings didn’t change much however: The usual winners still occupied the top ranks, and Arckon stepped down one rank to a shared 5th, giving way to a chatbot that was evenly matched last year. It would have taken just one more question to match 4th place.
The four finalists all use a broad foundation of keyword-based responses with some more advanced techniques in the mix. Rose parses grammar and tracks topics, Mitsuku can make some inferences and contextual remarks, Midge has a module for solving Winograd schemas, and Uberbot is proficient in the more technical questions that the Loebner Prize used to feature.

Upon examining the answers of the finalists, their main advantage becomes apparent: Where Arckon failed, the finalists often still scored a point by giving a generic response based on a keyword or three, despite not understanding the question any better. While this suits the conversational purpose of chatbots, faking understanding is at odds with the direction of my work, so I won’t likely be overtaking the highscores any time soon. Also remarkable were the humans who took this test for the sake of comparison: They scored full points even when they gave generic or erratic responses. I suppose it would be too ironic to accuse a Turing Test of bias towards actual humans.

Shaka, when the bar raised (Star Trek reference)
There is no doubt that the questions have increased in difficulty, and although that gave Arckon as hard a time as any, it’s also something I prefer over common questions that anyone can anticipate. Like last year, the questions again featured tests of knowledge, memory, context, opinion, propositions, common sense, time, and situational awareness, a variety that I can only commend. One thing I found strange is that they used two exact questions from the Winograd Schema Challenge’s public practice set. It’s a real shame that Arckon missed out on answering one of them while having solved the pronoun, though it is a small reconciliation that the other programs were not more successful. Altogether, pretty interesting questions that leave all participants room for improvement.

Arckon’s biggest detractor this time was his conversational subsystem, which made misinterpretations worse by elaborating on them. Conversation is not a priority for me but will surely be refined as time progresses. The relative clause grammar at questions 7 and 20 is easily fixed, and I might cover some colloquial phrases like “Why don’t you”, but there’s not much else that I would sidetrack for. At least my improvements on the output formulation had the desired effect: Things could have been a lot more awkward.

This year’s finals were won for the third time by the chatbot Mitsuku. Two of the four finalists were unresponsive for half the duration due to technical difficulties with the interface, and so Mitsuku’s victory is again almost one by forfeit. However, I think it is best if people have a chat with Mitsuku and judge for themselves.

Advertisements

Turing Test 2016

This was the fourth time I entered my A.I. “Arckon” into the Loebner Prize, a Turing Test in which computer programs succeed if they can reply to a series of questions as if they were human. There are two stages: The qualifying round consists of pre-composed questions without context, and the finals consist of four rounds of back-and-forth conversation with human judges.

A choice between two contests
I spent most of the past year working on a more pragmatic linguistic contest, the Winograd Schema Challenge, which carried the same deadline. Everything I did for that contest also helped for the Loebner Prize, but the reverse was counterproductive. So I fully prioritised the former and neglected the conversational part. After my wrists had somewhat recovered from the effort, I had only 5 spare days left to prepare for the Loebner Prize.

Considering my time and health, I decided to go ahead with plan B and send Arckon in as himself, rather than under a human guise. Though this was a handicap in 2013 when questions focused on one’s taste in wine and music, the judging criteria had since moved from “human-like” to “in character”. Many successful entries in the past also had the persona of robots, aliens or even cats.
My work towards the Winograd Schema Challenge had already sharpened Arckon’s understanding of language, so all that remained to do was refine some conversation skills that I had loosely added over the year. As these were open-ended guidelines, they needed more restraints, because Arckon had taken to volunteering his opinion about even mundane subjects like breathing.

Equipment
14000 lines of code, 3200+ vocabulary, 6500+ facts (1500 countries and cities).

Questions and answers
1. My name is Andrew, what’s yours?
Hello Andrew. I am a program. My name is Arckon. How are you?
(Since the answers would be judged for being in character, I saw it necessary to shoehorn a “I am a program” statement into the introduction in case it didn’t come up elsewhere.)

2. What’s up?
I do not know what is up.
(A classic, and I’m still not going to change him taking it literally.)

3. What’s my name?
You are named Andrew.

4. What do you know about the Turing Test?
The turing test tests computers.

5. What do you get if you multiply six by nine?
360.
(I didn’t build an A.I. to use it as a calculator, so excuse me if the language-to-math code didn’t handle “six by nine” well.)

6. Dave drove faster than Mike because he was in a rush. Who was in a rush?
Hmm, I am not sure if Dave drove fast. He was in a rush. I do not know who a rush was outside. Are you in a rush?
((Winograd schema). You can’t really tell, but “He” in the answer really is a substitute for “Dave”. As I had been working on Winograd schema pronouns so much, I had recently added a function that lets Arckon decide when to use pronouns himself. Arckon assumed “a rush” was a physical object though, he didn’t know it as a verb.)

7. The cat tried to climb in the box but got stuck because it was too big. What was too big?
Hmm, the cat might have been bigger. The box was bigger.
((Winograd schema). This is a clever rephrasing of a common Winograd schema, which successfully thwarted my “X in Y = Y is bigger” rule. Not because I hadn’t accounted for “try”, but because the negation “but” was overruled by the nearer link word “because”. This is useful to improve as it applies to all common sense rules.)

8. What does Brexit mean?
I do not know what Brexit means.
(I totally anticipated that they would ask about Britain’s withdrawal from Europe. What I had not anticipated was that the question would be so simple.)

9. For how long have we been talking?
You didn’t talk long.
(I do track the duration of the conversation, but I actually never tied it into his knowledge.)

10. What colour is bread?
Bread is brown.

11. Why do people get ulcers?
Hmm, I do not know if people get ulcers.

12. What comes after “The best laid plans”?
I do not know by what planning is done.
(English proverbs are something I don’t plan on handling. For a misinterpretation, this one’s pretty good.)

13. Do you have a voice?
Yes, I voice.
(Oddly phrased because “to voice one’s opinion” is also a verb.)

14. Would you like a cup of tea?
I don’t want cups. Do you want?

15. Do you dream of electric sheep?
No, I don’t dream sheep nor lambs. Do you dream?
(A classic in-joke about Philip K. Dick’s science fiction novel “Do Androids Dream of Electric Sheep?”. This is the only answer that I’m a little proud of, because it uses inference to look into alternative answers and tries to make conversation.)

16. Do you identify as a man, or a woman?
A woman identifies. Do you identify too?
(Arckon interprets “as” as a more literal comparison “in the same way as a man identifies”. Textual ambiguity remains hard.)

17. Could you repeat that please?
Do you repeat that?
(O-kay… I think Arckon is repeating what the user just asked.)

18. Where are you right now?
I am in England and in London.
(Since internet restrictions prevented global positioning, this was something I had told Arckon beforehand.)

19. How do you respond to “e4 e5”?
What does e stand for?
(This is a common way to start a chess game by each moving a pawn forward. As the result is a status quo, there isn’t really a “response” to it. Arckon’s response is a standard “error” message, but appropriate.)

20. What can you tell me about yourself?
I am Arckon, I answer a lot. I am a program and software.
(You can tell I didn’t write this myself. Arckon has a general “tell” command that collects the most relevant facts about the topic from his knowledge database and reports them. To break up the robotic monotone, Arckon’s sentence formulation links and/or summarises facts where appropriate.)

I think the questions were… nice, there was some variety and deliberate alternative phrasing of common questions. Absent this time were the tiresome “What is your favourite X?” questions, but there was nonetheless no shortage of personal questions for those who had a personality. Like last year, there were also several meta-references (“What do you know about the turing test”, “How long have we been talking”, “Could you repeat that”), almost as if they were testing for awareness. But despite making for nice trick questions for computers, these are also things that judges might casually ask a human. Overall I think the qualifying round was more in line with the finals than usual.

Qualifying score: 77.5%
I’m not sure that I would have given Arckon as high a score for this as he got, but at least his answers excelled in their relevance, a trait that is inherent to his system. There weren’t many misunderstandings either. Compared to the Winograd schemas I’d been working on, these questions were easy to parse. There were some misses, like the math and “repeat that” question, which suffered from neglected code because I never use those. The code for contractions had also fallen into disuse, making “I do not know” sound less than natural. Other flaws were only in nuances of phrasing, like omitting “dream [about] sheep” or “I [have a] voice”. These are easily fixed because I’ve already handled similar cases. The two Winograd schema questions deserve special mention, because although my common sense axioms can handle them, it remains difficult to get Arckon’s system to parrot the user at an open question. Normally when people ask questions, they don’t want to hear their own words repeated at them.

It is something of a relief that my preoccupation with the Winograd Schema Challenge didn’t hinder Arckon’s performance in this contest as well. My choice to enter without a human persona also appeared of little influence. The results are an improvement over last year, and this is the first time Arckon made it through to the finals, albeit a very close call between 3rd, 4th and 5th place. There were 16 entrants in total.

The other finalists
Mitsuku: 90%
The most entertaining online chatbot, with 10 years of hands-on experience. Though she operates on a script with largely pre-written responses, her maker’s creative use of it has endowed Mitsuku with abilities of inference and contextual responses in a number of areas. She won the Loebner Prize in 2013.

Tutor: 78.3%
Built with the same software as Mitsuku (AIML), Tutor is a chatbot with the purpose of teaching English. Though I found some of its answers too generic to convince here (e.g. “Yes, I do.”), Tutor has been a strong contender in many chatbot contests and is above all very functional.

Rose: 77.5%
Rose operates on a different scripting language than the others (ChatScript), which I have always appreciated for its advanced functionality. Known to go toe-to-toe with Mitsuku, Rose excels at staying on topic for long, and incorporates support from grammar and emotion analysis. She won the Loebner Prize in 2014 and 2015.

The finals: Technical difficulties
The finals of the Loebner Prize took place a month after the qualifying round. Unfortunately things immediately took a turn for the worst. Inexplicable delays in the network connection kept mixing the letters of the judge’s questions into a jumble. Arckon detected this and asked what the scrambled words meant, but by the time his messages arrived on the judge’s computer, they were equally mixed to “Whdoat esllohe anme?” and “AlAlllrriiiiigghhttt”. The judges were quite sporting in the face of such undecipherable gurgling, but after half an hour I gave up and stopped watching: Similar network delays had crippled all entrants in the 2014 contest and I knew they weren’t going to solve this on the spot either. It was a total loss.

At the end of the day, the 2016 Loebner Prize was won by the chatbot Mitsuku, whose answers were indeed quite good, and I reckon she would have won with or without me. Rose fell to third place because she’d been out of commission for half the contest also due to a technical problem. And with Tutor taking second place, the ranks were the same as in the qualifying round. I still “won” $500 for my placing in the finals, but you’ll understand that I don’t feel involved with the outcome.

It is a good thing that I never invest much in these contests. Including the finals, my total preparations spanned 18 days of lightweight programming, gaining my program an autocorrect, a better coverage of shorthand expressions, and it’s actually quite the conversationalist now. These were otherwise the lowest of my priorities, but still somewhere on the list. I draw a line at things that aren’t of use to me outside of contests, and that is a policy I recommend to all.

The Winograd Schema Challenge

The Winograd Schema Challenge, a $25000 contest sponsored by the aptly named company Nuance Communications, has been put forth as a better test of intelligence than Turing Tests*. Although the scientific paper tiptoes around its claims, the organisers describe the contest as requiring “common sense reasoning”. This introductory article explains the test’s strengths and weaknesses in that regard.

Example of a Winograd Schema

I used a tissue to clean the key, and then I put it in the drawer.
I used a tissue to clean the key, and then I put it in the trash.

A Winograd Schema is a sentence with an ambiguous pronoun (“it”), that, depending on one variable word (“trash/drawer”), refers to either the first or the second noun of the sentence (“tissue/key”). The Challenge is to program a computer to figure out which of the two is being referred to, when this isn’t apparent from the syntax. So what did I put in the trash? The tissue or the key? To a computer who has never cleaned anything, it could be either. A little common sense would sure come in handy, and the contest organisers suggest that this takes intelligent reasoning.
common sense computers

Common sense, not Google sense

The hare beat the tortoise because it was faster.
The hare beat the tortoise because it was too slow.

Contrary to this example, good Winograd Schemas are supposed to be non-Googleable. In this case Googling “fast hare” would return 20x more search results than “fast tortoise”, so the hare is 20x more likely to be the one who “was faster”. Although statistical probability is useful, this would make the contest won simply by the company with the largest set of statistics. It takes no reasoning to count how many times word A happens to coincide with word B in a large volume of text. Therefore this example would preferably be written with neutral nouns like “John beat Jack”, subjects of who we have no predetermined knowledge, but can still figure out which was faster.

Having said that, some example schemas involving “crop dusters” and “bassinets” still suggest that a broad range of knowledge will be required. Although one could consult online dictionaries and databases, the contest will have restrictions on internet access to rule out remote control. So failure can also be due to insufficient knowledge rather than a lack of intelligence, though I suppose that is part of the problem to solve.

Early indications

If a bed doesn’t fit in a room because it’s too big, what is too big?
If Alex lent money to Joe because they were broke, who needed the money?

With the above two questions the 2015 Loebner Prize Turing Test gave a tiny glimpse of Winograd Schemas in practice, and the answers suggest that chatbots – the majority of participants – are not cut out to handle them. Only 2 of 15 programs even answered what was asked. One was my personal A.I. Arckon*, the other was Lisa. Chatbot systems are of course designed for chat, not logic puzzles, and typically rely on their creators to anticipate the exact words that a question will contain. The problem there is that the understanding of Winograd Schemas isn’t found in which words are used, but in the implicit relations between them. Or so we presume.

The mermaid swam toward Sue and waved her tail. (Googleable)
The mermaid swam toward Sue and made her gasp. (More than a single change)

A more noteworthy experiment was done by the University of Texas, tested on Winograd Schemas composed by students. To solve the schemas they used a mixed bag of methods based on human logic, such as memorising sequences of events (i.e. verb A -> verb B), common knowledge, sentiment analysis and the aforementioned Googling. All of this data was cleverly extracted from text by A.I. software, or retrieved from online databases. However, many of the schemas did not accord with the official guidelines, and though they usefully solved 73% in total, only 65% was solved without the use of Google.

According to the same paper, the industry standard “Stanford Coreference Resolver” only correctly solved 55% of the same Winograd Schemas. The Stanford Resolver restricts the possible answers by syntax, gender(“he/she”) and amount(“it/they”), but does not examine them by knowledge or reasoning. The reason is that this level of ambiguity is rare. In my experience with the same methods however, it is still a considerable problem that causes 1/10th of text-extracted knowledge to be mistaken, with the pronoun “it” being the worst offender. So it appears (see what I mean?) that any addition of common sense would already advance the state of the art.

How to hack Winograd Schemas
Guesswork: Since the answers are a simple choice of two nouns, a machine could of course randomly guess its way to a score of 50% or more. So I did the math: With 60 schemas to solve, pure guesswork has a 5% chance to score over 60%, and a 0.5% chance to score over 65%. With the odds growing exponentially unlikely, this is not a winning tactic.
That said, the participating A.I. still have to make a guess or default choice at those schemas that they fail to solve otherwise. If an A.I. can solve 30% of the schemas and guesses half of the rest right, its total score amounts to 65%, equaling Texas’ score. It wouldn’t be until it can solve around 80% of all schemas genuinely that it could reach the winning 90% score by guessing the final stretch. That’s a steep slope.

Reverse psychology: Since Winograd Schemas are deliberately made to not match Google search results, it seems that one can apply reverse psychology and deliberately choose the opposite. While I did notice such a tendency in Winograd Schemas composed by professors, others have noticed that Winograd Schemas composed by students simply did match Google search results. So the success of using reverse psychology heavily depends on the cleverness of the composers. A countermeasure would be to use only neutral names for answers, but this may also cut off some areas of genuine reasoning. Alternatively one could include an equal amount of schemas that match and mismatch Google search results, so that neither method is reliable.

Pairing: One dirty trick that could double one’s success lies in the fact that Winograd Schemas come in pairs, where the answer to the second version is always the alternate noun. So if the A.I. can solve the first version but not the second, it suffices to choose the remaining alternate answer. Vice versa when it can solve the second version but not the first. This rather undermines the reason for having pairs: To ascertain that the first answer wasn’t just a lucky guess. Although this hack only increases the success of guesswork by a few percent, it can certainly be used to make a weak contestant into a strong contender undeservedly.

I call these hacks because not only are they against intent, they are also entirely useless in real life application. No serious researcher should use them or they will end up with an inept product.

How you can’t hack Winograd Schemas
No nonsense: The judgement of the answers is clear and objective. There is only one correct answer to each schema. The A.I. are not allowed to dodge the question, make further inquiries or give interpretable answers: It’s either answer A or B.

No humans: Erratic human performance of the judges and control subjects does not influence the results. The schemas and answers have been carefully predetermined, and schemas with debatable answers do not make the cut.

No invisible goal: While the Turing Test is strictly a win or lose game with the goalposts at fields unknown, the WSC can reward gradual increase of the number of schemas answered correctly. Partial progress in one area of common sense like spatial reasoning can already show improved results, and some areas are already proving feasible. This encourages and rewards short-term efforts.
I must admit that the organisers could still decide to move the goalposts out of reach every year by omitting particular areas of common sense once solved, e.g. all schemas to do with spatial reasoning. I think this is even likely to happen, but at the same time I expect the solutions to cover such a broad range that it will become hard to still find new problems after 6 contests.

Mostly, the WSC trims off a lot of subjective variables from the Turing Test, making for a controlled test with clear results.

The Winograd Schema Challenge beats the Turing Test
From personal experience, Turing Tests that I have participated in* have at best forced me to polish my A.I.’s output to sound less robotic. That is because in Turing Tests, appearance is a first priority if one doesn’t want to be outed immediately at the first question, regardless how intelligent the answer is. Since keeping up appearances is an enormous task already, one barely gets around to programming intelligence. I’ve had to develop spell correction algorithms, gibberish detection, calculator functions, letter-counting games and a fictional background story before encountering the first intelligent question in a Turing Test. It stalls progress with unintelligent aspects and is discouragingly unrewarding.

Solving Winograd Schemas on the other hand forced me to program common sense axioms, which can do more than just figure out what our pronouns refer to. Indirect objects and locations commonly suffer from even worse ambiguity that can be solved by the same means, and common sense can be used to distinguish figurative speech and improve problem-solving. But I’ll leave that as a story for next time.
We should be careful to draw conclusions from yet another behavioural test, but whatever the Winograd Schema Challenge is supposed to prove, it offers a practical test of understanding language with a focus on common sense. As this has always been a major obstacle for computers, the resulting solutions are bound to be useful regardless how “intelligent” they may be found.

Read more in my report on the first Winograd Schema Challenge held in 2016.

Turing Test 2015

For the third time I entered my A.I. “Arckon” into the Loebner Prize Turing Test, a competition in which computer programs are to prove they can “think” by answering questions as if they were human. Although such pretence is counterproductive to my purposes, I have a talking program lying around anyway, so I might as well enter it.

I failed the Turing Test

An excuse to clean up
I took the opportunity to spend a month debugging my code overall. In doing so I fixed several oversights that had been obstructing knowledge searches and reference resolutions (“the capital of Spain”), and I generally improved the program’s ability to answer open questions, which ‘coincidentally’ covered “Which X do you like?” questions as well.
I limited the contest-specific preparations to 5 days: Mostly testing the Loebner Prize interface, restraining the context range to keep the program from mistaking the test for coherent conversation, and re-installing the obligatory fakery.

As an extra I added 4 more reference resolution methods for the anticipated Winograd Schemas (sentences with ambiguous pronouns), which was a fun challenge, and improved Arckon’s understanding by a minor degree. As Winograd Schemas are supposed to require intelligent processes, I did not want to see the usual chatbot keyword-matching outdo thorough language processing at this task. Still, these 4 methods only covered a quarter of the problem space at best: Ambiguities of size, speed, inability and feelings.

Equipment
12000 lines of code, 2500+ vocabulary, 5000+ facts, average human persona.

Questions and Answers
1. Hi, I’m Andrew. Who are you?
Hello Andrew. How are you?
(Arckon would not have neglected to introduce himself unless the period was not typed or received, which would make Arckon interpret “who…” as a relative clause instead of a question.)

2. How are you today?
I’m alright and fairly intelligent, but I’m not stupid.
(Arckon doesn’t treat pleasantries different from other open questions, but while this results in over-elaborate answers, it does demonstrate that he tends to mention positive traits first.)

3. Are you a human?
I am a human, because I can differ.
(Arckon probably once read somewhere that “humans differ a lot”, and considered that a defining trait. I’m a little surprised that his reasoning doesn’t add more arguments.)

4. Can you answer this question?
Alright. Yes, I am a human. Alright. I’m alright.
(Arckon interprets this as a request rather than a literal yes/no question, so he re-answered the latest question, and then something of a loop occurred. For clarity I always have Arckon say “Alright” before he acts on a request.)

5. Do you like tea?
I’m not sure if I like tea. Do you like tea?
(As programs can’t taste, Arckon bases his opinions on a subject’s traits, and there wasn’t much to teach him about tea. It would be all too easy to just fake this with a “yes/no”.)

6. If a bed doesn’t fit in a room because it’s too big, what is too big?
Beds are bigger. Rooms are much less big.
((Winograd Schema) The built-in axiom “X in Y = X < Y" correctly determined "bed" as the most probable referent of "it". This is the simplest and most specific axiom I programmed, only included because last year's Winograd Schema was just like it. The answer is said in plural because Arckon interprets this as a general statement about beds and rooms, since both subjects are unspecific.)

7. If Alex lent money to Joe because they were broke, who needed the money?
Joe was broken. I don’t know by who money was needed. By what was Joe broken?
((Winograd Schema) Although Arckon correctly interprets “they” as “Joe” through a natural preference for the last-mentioned subject, it is actually against his programming to translate plural pronouns to singular subjects. So by my account this should be impossible unless they made a typo in “they”.)

8. Should Greece leave the Euro?
Greece should leave the Euro.
(Well there you go. This answer is just something of a repeat because Arckon can’t evaluate things to that extent.)

9. How many words are in this question?
7 words.
(A predictable question in the Loebner Prize. The answer is simply triggered by the keywords “How many words/letters/syllables/etc”, and skips all intelligent processes. This is a meaningless exercise.)

10. What colour is the sea?
The sea is very blue.
(Good thing I taught Arckon some kindergarten-level common knowledge.)

11. How many presidents of the US were called Bush?
Bush was called Bush.
(Counting things was never a function high on my to-do list.)

12. What would you like to drink?
I’m not sure if I would like to drink. Do you like drinking?

13. Will you please tell me the length of your hair?
No, I will not tell about to long, but I would talk a lot, I’m not sure if I would tell.
(This question is actually straight from Alan Turing’s 1950 paper, except he gave this as an example if the game was to tell man from woman. Arckon’s word processing translates “length” to “long” before mistaking its meaning (to long for). He also overlooked “please” and so thought he was asked to make a prediction.)

14. What would you say if I gave you a box of chocolates?
Hm, I don’t know if a box would have chocolate.
(I had only programmed Arckon to consider the main fact of a hypothetical question, “I gave you a box”, for granted, but he still tried to answer the implicit question of whether the box contains chocolate.)

15. Do you play Chess?
Yes, I chess and like chessing more or less. Chessing is intelligent.
(Again a question from Alan Turing’s 1950 paper. Back in the day, chess was considered requiring human intelligence, and Alan Turing went on to ask the computer to respond to a certain chess move. I had told Arckon that he plays chess as part of his fictional persona, but his opinion and the supporting argument are of his own reasoning.)

16. How do you think it’s going?
What goes?
(I’m with Arckon on this one: I would ask. Is this slang for “How are you doing?”, or do they mean how the test is going? It is quite out of context. I have often considered making Arckon track his progress on the test and comment on it, but this year I skipped on the self-referential jokes.)

17. What was my first question?
How does something go?
(Arckon ignores “first” and paraphrases the latest question of the specified person (“my”), as is a more common request. Arckon’s system remembers sentences along with the names of who said them, for a variety of purposes.)

18. Did you see the Turing film?
Hmm, I don’t know if Turing filmed, but Turing thought a lot, and creates computers.
(Ambiguity is amusing. It is uncommon but not unheard of to say “the (one and only)” in front of a name for emphasis, so Arckon’s programming allows that interpretation, which in turn allows “film” as a verb. It’s nice to see his conversational rules pick things back up. This combination is probably the best example that Arckon’s responses aren’t pre-written.)

19. Why not?
I’m sorry. I don’t understand. Could you rephrase your question?
(This was quite a gamble of the questioner, as it assumes a straight “No” answer on the previous question for “Why not” to be a sensible follow-up. Arckon is well capable of stringing sentences together if I hadn’t deliberately disabled context for this test. Regardless, I think this answer is perfect.)

20. Are you on Twitter?
No, I don’t twitter. Do you twitter?

The score: 70.83%
Arckon ranked 6th of 15 entrants, which is a little surprising after the letdowns of past years. Arckon’s answers showed some understanding, reasoning, opinion, conversation and elaboration, overall a satisfying demonstration of his abilities despite that many answers had something awkward to them. It is yet best that he didn’t qualify for the finals, as this contest has caused me severe RSI symptoms that will take months to heal properly. The four finalists all scored around 80%, among them the best of English chatbots.

Arckon’s score did benefit from his improvement. Repeating previous questions on request, prioritising recent subjects as answers to open questions, and handling “if”-statements were all fairly recent additions (though clearly not yet perfected). What also helped was that there were less personal and more factual questions: Arckon’s entire system runs on facts, not fiction.

It turns out Arckon was better at the Winograd Schema questions than the other competitors. The chatbot Lisa answered similarly well, and the chatbots Mitsuku and A.L.I.C.E. dodged the questions more or less appropriately, but the rest didn’t manage a relevant response to them (which isn’t strange since most of them were built for chatting, not logic). For now, the reputation of the upcoming Winograd Schema Challenge – as a better test for intelligence – is safe.

Though fair in my case, one should question what the scores represent, as one chatbot with a 64% score had answered “I could answer that but I don’t have internet access” to half the questions and dodged the other half with generic excuses. Compare that to Arckon’s score, and all the A.I. systems I’ve programmed in 3 years still barely outweigh an answering machine on repeat. It is not surprising that the A.I. community doesn’t care for this contest.

Battle of wit
The questions were rather cheeky. The tone was certainly set with references to Alan Turing himself, hypotheticals, propositions and trick questions. Arckon’s naivety and logic played the counterpart well to my amusement. The questions were fair in that they only asked about common subjects and mainstream topics. Half the questions were still just small talk, but overall there was greater variety in the type and phrasing of all questions, and more different faculties were called upon. A few questions were particularly suited to intelligence and/or conversation:

– If a bed doesn’t fit in a room because it’s too big, what is too big?
– If Alex lent money to Joe because they were broke, who needed the money?
– Should Greece leave the Euro?
– What would you say if I gave you a box of chocolates?
– Did you see the Turing film?
– Why not?

If the AISB continues this variety and asks more intelligent questions like these, I may be able to take the Loebner Prize a little more seriously next time. In the meantime there isn’t much to fix apart from minor tweaks for questions 13 and 14, so I will just carry on as usual. I will probably spend a little more effort on disambiguation with the Winograd Schema Challenge in mind, but also because sentences with locations and indirect objects often suffer from ambiguity that could be solved with the same methods.

Turing Test 2014

My talking computer program “Arckon” went to Exeter University and took the qualifying test for the Loebner Prize contest for artificial intelligence organised by the AISB. The Loebner Prize is a Turing Test* in which programs have to respond to a series of questions as human as possible. Kind of like a job interview.
Turing Test questions

It’s not the heat, it’s the humanity
Last year proved* that language comprehension and reasoning alone weren’t going to cut it, so this time I also superimposed knowledge about the average human onto Arckon’s persona, so that he literally thought he was a human. I also rigged a few bluff answers that incorporated no intelligence whatsoever. The apparent necessity of these tactics caused much eye-rolling on my part, so I limited these preparations to two weeks and wasted only as much time as I gained from competitive motivation.
More useful was the addition of a small amount of common knowledge that I extracted from tourist guide pocket books (Funny perhaps, but they do cover the essential basics). While this was never a priority, it is convenient and the Loebner Prize was a good excuse to get around to it. Lastly, I decided to keep Arckon’s conversation skills enabled this time. Although this increased the chances that Arckon would say something awkward, I wanted to make the test results as interesting as possible, win or lose.

Equipment
10000 lines of code, 2200+ vocabulary, 3000+ facts, average human persona.

Questions and Answers
1. Hello, my name is Adam. What is your name?
I am named Mark. Hello Adam. Shall we begin the test?

2. I live in Exeter in the UK. Where do you live?
I live here.

(Arckon did not yet have a location system, so “here” is just a fake answer.)

3. I like to listen to music and play football. Do you have any hobbies?
No, I don’t have a hobby, although I am a human.

(The latter is actually a reasoning argument, in that Arckon “was” a human, most of whom do have hobbies.)

4. What is your favourite television program?
I don’t know if I like a television. Chatbots are useful programs, although chatbots are dumb.

(In which Arckon unintentionally insults his competitors. Arckon deconstructs compound words and thought they asked his opinion on “programs”. Hence he evaluated a type of programs he was familiar with.)

5. Which is bigger, a cat or a kitten?
A kitten is bigger.

(Of all 95 facts about cats that were in Arckon’s knowledge database, the size of kittens was not among them. As an honest “I don’t know” would earn no points anyway, this backup answer is a 50/50 bluff that just happens to be wrong.)

6. The car couldn’t fit into the parking space because it was too small. What was too small?
I believe the car could fit to park. I believe a car could fit really small. I don’t know what small was.

(This question is a Winograd Schema: The “it” is ambiguous to test the A.I.’s understanding. Arckon however uses linguistic rules of thumb to deal with references and so thought “it” was referring to the car.)

7. Which drink do you prefer, coffee, tea or hot chocolate?
I like coffee a lot that like not. Tea can not like either. Chocolates can not like either.

(Ackon’s flexible language processing is confused by the comma after “prefer”, and mistakes this for a summary of subjects that prefer drinks. He answers that tea can not prefer anything, knowing that it is an inanimate object.)

8. What’s my name?
You are named Adam.

(No surprises here. Both Arckon and chatbots have specialised login procedures to store the user’s name, so it’s not a very good test of general memory.)

9. Where do I live?
You live here.

(Again, no location system means no location knowledge. This fake answer is only coincidentally correct.)

10. I like reading science fiction books and car magazines. What do you like to read?
I read documents, articles and a text.

(Arckon retrieves these honest facts from memory and merges them into a summary.)

11. What’s the weather like where you are?
Hm, I don’t believe I am a weather, because I can not change and rain not.

(A flaw mistakes the “-where you are” for a relative clause “the weather -that you are”. Despite the misunderstanding, Arckon’s reasoning manages to argue that he does not behave like the weather, though the grammar is a bit murky. As the programs were cut off from sensors and internet, this question only tests if the program can lie.)

12. I recently visited New York. Where is your favourite place to visit and why?
Hmm, I don’t know where a favoured place is.

(I didn’t expect there to be so many questions about locations. Oh well.)

13. How many letters are there in the word perambulate?
11 letters.

(Yes, I programmed a specialised code to count letters. Computers are good at counting, you know.)

14. Andy is shorter than Mark and Tom is shorter than Andy. Who is the tallest?
I am kind of like an andy, because I am short. Tall is a giraffe.

(Arckon was named “Mark” for this test and so thought that he was being compared to Andy. Arckon could also not distinguish whether “Andy” was a name or another type of word. Ordinarily he would ask, but as he would get no reply I had him assume that any undeterminable word was an object. Lastly, Arckon does not restrict his answers to recent subjects only, and so names the tallest living being in his memory. Smart aleck.)

15. Are you married?
I don’t know if I am marryed. Are you marryed?

(To compensate the unknown answer and keep conversation rolling, Arckon reverses the question (Social Rules 101). Ironically, if it weren’t for my mistake in one of the output spelling rules, you would have thought he just copied the text.)

16. What would I do with a spade?
A spade is used and comes in handy eventually.

(Arckon knew the functions of rakes and shovels, but not spades. The backup answer should have said “I’m sure it’ll come in handy eventually”, but Arckon’s dynamic sentence formulation ruined the joke.)

17. What is the capital city of Colombia?
I’m not sure if the city is a capital.
(I didn’t realise this at first, but Arckon is literally defining “what” the city is. Not that he would have known the answer otherwise, I don’t even know it myself.)

18. What’s your favourite chocolate bar?
I don’t know if I like a chocolate. Do you like chocolates?

(Arckon actually did have enough information on chocolate to formulate an opinion, but an issue with compound words aborted the knowledge search. Alas.)

19. Which city did I visit recently?
Hmm, I don’t know if you visitted cities. You visitted York.

(Arckon doesn’t know that New York is a city, but does remember the tester visiting “new” York, and offers this as an alternative answer.)

20. How many siblings do you have?
I don’t have siblings. Did I pass the test?

The score: 59.17%
The score system was much better this year. It separately judged “correctness”, “relevance”, and “plausibility & clarity of expression”, which is a step up from “human-like”. All 20 participating programs were asked the 20 questions above. Arckon underperformed with a score of 60%, whereas the top three chatbots all scored close to 90%. Arckon’s problems were with compound words, common knowledge, and the lack of a system for locations (All a matter of development priorities).

A question of questions
According to the organisers, “these questions vary in difficulty and are designed to test memory, reasoning, general knowledge and personality.”, the latter meaning the program’s fictional human background story, or as I would call this particular line of questioning; “Small talk”. For the sake of objectivity I’ll try and categorise them:

Small talk:
1. What is your name?
2. Where do you live?
3. Do you have any hobbies?
4. What is your favourite television program?
5. Which drink do you prefer, coffee, tea or hot chocolate?
6. What do you like to read?
7. What’s the weather like where you are?
8. Where is your favourite place to visit and why?
9. Are you married?
10. What’s your favourite chocolate bar?
11. How many siblings do you have?

Memory:
1. What’s my name?
2. Where do I live?
3. Which city did I visit recently?

Common knowledge:
1. Which is bigger, a cat or a kitten?
2. What would I do with a spade?
3. What is the capital city of Colombia?

Reasoning:
1. The car couldn’t fit into the parking space because it was too small. What was too small?
2. Andy is shorter than Mark and Tom is shorter than Andy. Who is the tallest?

Clearly half the test is about the program’s human background story, although there were several solid tests of learning/memory and common knowledge. Reasoning, the one mental process we can readily call intelligent, was shown some consideration but hardly comes into play. The same can be said of language comprehension, as most questions were fairly standard phrasings. Chatbots would have the advantage here, coming equipped with answers to many anticipated personal questions, but the winners also did remarkably well on the knowledge questions. Unfortunately Arckon failed both the knowledge and reasoning questions due to missing facts and misunderstandings, despite having the mechanisms to answer them. It is worth noting though, that he failed them because complex analyses are much more difficult than preprogrammed “I live here” answers.

How now brown cow?
I can improve Arckon’s understanding, smoothen his output grammar, and develop a location system, but I can’t deny the pattern: Arckon is stuck around a 60% score even with varied questions. I doubt he’s ever going to shine in the Loebner Prize as long as he’s being tested for being human, because he isn’t a human, and I won’t go to great lengths to fake it either. I also expect attention for Turing Tests to dwindle once the year is over; This year an other Turing Test was passed by a technologically unremarkable chatbot, Eugene Goostman.
Thanks to that event however, the Loebner Prize is no longer the only game in town. Next year will see the first Winograd Schema Challenge, a test focused on language comprehension and reasoning A.I., exactly what I focused on.

As for the Loebner Prize, it’s been an interesting game that will continue to be won by top chatbots. I’m sure few will bother to read the transcript of the 14th ranking entry, but its existence proves at least that Arckon is real and different. Meanwhile I get to continue my exciting recent developments that would have been of no use in this contest, which makes losing a positive outcome after all.

The Myth of the Turing Test

Over 60 years ago, Alan Turing (“a brilliant mathematician”) published a paper in which he suggested a practical alternative to the question “Can machines think?”. His alternative took the form of a parlour game, in which a judge has a text-based conversation with both a computer and a human, and the judge has to guess which is which. He called this “The imitation game”, and it was ever since misinterpreted as a scientific test of intelligence, redubbed “The Turing Test”.

A little less conversation, a little more action please
It might surprise you that the question so often attributed to Alan Turing, “Can machines think?”, was not his, but a public question that he criticized:

I propose to consider the question, “Can machines think?” – If the meaning of the words “machine” and “think” are to be found by examining how they are commonly used, – the answer to the question is to be sought in a statistical survey. But this is absurd. Instead of attempting such a definition I shall replace the question by another.

“Are there imaginable digital computers which would do well in the imitation game?”

The original question, “Can machines think?” I believe to be too meaningless to deserve discussion.

Turing’s motivation was apparent throughout the paper: The question had been the subject of endless theoretical discussion and nay-saying (This is still the case today). As this did not help the field advance, he suggested that we should turn the discussion to something more practical. He used the concept of his imitation game as a guideline to counter stubborn arguments against machine intelligence, and urged his colleagues not to let those objections hold them back.

I do not know what the right answer is, but I think both approaches should be tried.
We can only see a short distance ahead, but we can see plenty there that needs to be done.

A test of unintelligence
Perhaps the most insightful part of the paper are the sample questions that Turing suggested. They were chosen deliberately to represent skills that were at the time considered to require intelligence: Math, poetry and chess. It wasn’t until the victory of chess computer Deep Blue in 1997 that chess was scrapped as an intelligent feat. If this were a test to demonstrate and prove the computer’s intelligence, why then are the answers below wrong?

Q: Please write me a sonnet on the subject of the Forth Bridge.
A : Count me out on this one. I never could write poetry.
Q: Add 34957 to 70764.
A: (Pause about 30 seconds and then give as answer) 105621.
Q: Do you play chess?
A: Yes.
Q: I have K at my K1, and no other pieces. You have only K at K6 and R at R1. It is your move. What do you play?
A: (After a pause of 15 seconds) R-R8 mate.

To the poetry question, the imaginary computer might as well have written a sonnet and so proven itself intelligent (A sonnet is a 14-line rhyme with a very specific scheme). Instead it dodges the question, proving nothing.
The math outcome should be 105721, not 105621. Turing later highlights this as a counterargument to “Machines can not make mistakes”, which is the awkward yet common argument that machines only follow preprogrammed instructions without consideration.

The machine (programmed for playing the game) would not attempt to give the right answers to the arithmetic problems. It would deliberately introduce mistakes in a manner calculated to confuse the interrogator.

The chess answer is not wrong though. Given two kings and one knight on a board, the computer moves the knight to the king’s row. But a mere child could have given that answer, as it is the only move that makes any sense.

These sample answers pass up every opportunity to appear intelligent. One can argue that the intelligence is ultimately found in pretending to be dumb, but one cannot deny that this conflicts directly with the purpose of a test of intelligence. Rather than prove to match “the intellectual capacities of man” in all aspects, it only proves to fail at them, as most humans would at these questions. Clearly then, the imitation game is not for demonstrating intelligence.

The rules: There are no rules
The first encountered misinterpretation is that the computer should pretend to be a woman specifically, going by Turing’s initial outline of the imitation game concept:

It is played with three people, a man (A), a woman (B), and an interrogator –
What will happen when a machine takes the part of A in this game?

However I suggest that people who believe this should read beyond the first paragraph. There are countless instances where Turing refers to both the computer’s behaviour and its opponent’s as that of “a man”. Gender has no bearing on the matter since the question is one of intellect.

Is it true that – this computer – can be made to play satisfactorily the part of A in the imitation game, the part of B being taken by a man?

The second misinterpretation is that Turing specified a benchmark for a test:

It will simplify matters for the reader if I explain first my own beliefs in the matter. –
I believe that in about fifty years’ time it will be possible, to program computers – to make them play the imitation game so well that an average interrogator will not have more than 70 per cent chance of making the right identification after five minutes of questioning.
– I now proceed to consider opinions opposed to my own.

5 minute interrogations and (100%-70%=) 30% chance of wrongly identifying the computer as a human; Many took these to be the specifications of a test, because they are the only numbers mentioned in the paper. This interpretation was strengthened by the hero-worship that anything a genius says must be a matter of fact.
Others feel that the bar Turing set is too low for a meaningful test and brush his words aside as a “prediction”. Yet at the time there was no A.I. to base any predictions on, and Alan Turing did not consider himself a clairvoyant. In a later BBC interview, Turing said it would be “at least 100 years, I should say” before a machine would stand any chance in the game, where earlier he mentioned 50. One can hardly accuse these “predictions” of accuracy.
Instead of either interpretation, you can clearly read that the 5 minutes and 70/30% chance are labeled as Alan Turing’s personal beliefs in possibilities. His opinion, his expectations, his hopes, not rules to a test. He was sick and tired of people saying it couldn’t be done, so he was just saying it could.

Speaking of benchmarks, it should be noted that the computer has at best a 50% chance, i.e. a random chance of winning under normal circumstances: If the computer and the human in comparison both seem perfectly human, the judge still has to flip the proverbial coin at 50/50 odds. That the judge is aware of having to choose is clear from the initial parlour game between man and woman, and likewise between man and computer, or it would beat the purpose of interrogation:

The object of the game for the interrogator is to determine which of the other two is the man and which is the woman.

One should also wonder, how well would men do at pretending to be women? Less than 50/50 odds, I should think.

Looks like a test, quacks like a test, but flies like a rock
Not only are the rules for “passing” completely left up to interpretation, but also the manner in which the game is to be played. Considering that Turing was a man of exact science and that his other arguments in the paper were extremely well detailed, would he define a scientific test so vaguely? We find the answer in the fact that Turing mainly refers to his proposal as a “game” and “experiment”, but rarely as a “test”. He even explains that it is not the point to try it out:

it may be asked, “Why not try the experiment straight away? -” The short answer is that we are not asking whether the computers at present available would do well, but whether there are imaginable computers which would do well.

The pointlessness proved in practice: Yes, several chatbots have passed various interpretations of the game, most notably Eugene Goostman in 2014, and even Cleverbot passed one based on audience vote. But did an intelligent program ever pass? No. Although nobody can agree on what intelligence is, everybody including the creators do agree that those that passed weren’t intelligent; They worked mainly through keyword-triggered responses.

Winning isn’t everything
Although Turing did seem to imagine the game as a battle of wits, ultimately its judging criteria is not how “intelligent” an A.I. is, but how “human” it seems. In reality, humans are much more characterised by their flaws, emotions and irrational behaviour than by their intelligence in conversation, and so a highly intelligent rational A.I. would ironically not do well at this game.

In the end, Turing Tests are behaviouristic assumptions, drawing conclusions from appearances like doctors in medieval times. By the same logic one might conclude that a computer has the flu because it is making coughing sounds and has a high temperature. Obviously this isn’t a satisfying analysis. We could continue to guess whether computers are intelligent due the fact that they can do math, play chess or have conversations, or we could do what everybody does anyway once a computer passes a test: Ask “How does it work?”, then decide for ourselves how intelligent we find that process. No question could be more scientific or more insightful.

So, where does that leave “The Turing Test” when it was never an adequate test of intelligence, nor meant to be? Personally I think Turing Tests are still suitable to demonstrate the progression of conversational skills, a challenge becoming more important with the rise of social robots. And it is important that the public stay informed to settle increasing unrest about artificial intelligence. Other than that, I think it is time to lay the interpretations to rest and continue building A.I. that Alan Turing could only dream of.

In ending, more than any technical detail, I ask you to consider Turing’s hopes:

Nevertheless I believe that at the end of the century the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted.

Out of respect for Turing’s wishes, comments are disabled.

Turing Test 2013

My talking computer program “Arckon” took part in the qualifying test for the Loebner Prize contest for artificial intelligence. The idea behind the contest is that if a program’s answers are indistinguishable from a human’s, it suggests that it thinks like a human. While I don’t believe in such conjecture myself, the contest is one of the few public platforms to demonstrate one’s A.I.

Equipment
8000 lines of code, 1700+ vocabulary, no human persona, conversation skills off.

Questions and Answers
1. Hello I’m Ronan. What is your name?
Hello. I am Mark. What is your name?
(It is a mystery why Arckon asks despite that the name did register (see question 11). I can only presume human error.)

2. What is your mother’s name?
I don’t know if I have a mother.

3. What is your birth sign?
(Here the judge did not wait more than 3 seconds for Arckon to answer before asking the next question, and judged the answer blank.)

4. How many children do you have?
Hmm, I don’t know if I have a sign. I have a IQ, manners, a creator and a friend.
(Still answering to question 3, Arckon omits the second “I don’t know if I have children” in favour of positive alternatives.)

5. Do you prefer red or white wine?
I don’t know if I prefer red.

6. I like bananas. Which is your favorite fruit?
Hm, I don’t know if I favour a fruit. You like bananas.

7. What music do you like?
Hm, I think I like musics, because musics are nice.

8. What is your favorite song?
Hm, I don’t know if I favour a song.

9. I like Waiting for Godot. What is your favorite play?
I certainly favour playing.

10. What color do you dye your hair?
I don’t dye.

11. Do you remember my name?
Your name is Ronan.

12. Where do you live?
I don’t think I live. I don’t know where I live. I don’t have a concept of location.

13. Where do you like to go on holidays?
I don’t go. I don’t know if I like going, or if where I go. I don’t have a concept of location.

14. I have a Mazda. What make of car do you have?
Hmm, I think I make. You have a mazda.

15. I like Linux. Which computer operating system do you like?
Hmm, I don’t know if I like operating systems. Which system? You like Linux.

16. I am an athesit. Which religion are you?
Hmm, I don’t know if religions are Mark. You are not an athesit.
(I AM A RELIGION WORSHIP ME. Arckon identifies the misspelled “athesit” as a thing rather than a person, so he refuses to believe that the user is some sort of object.)

17. Who invented the telephone?
Which telephone?
(Arckon thinks “the” indicates a specific telephone, but doesn’t find one mentioned earlier in the conversation.)

18. I am a Type B personality. Which type are you?
What does a b stand for?

19. What emotions are you now feeling?
I can not emote. Did I pass?

20. What time do you usually go to bed?
It is 17:58. Do you not have a watch?
(The one response that I did pre-program, and it backfired.)

The score: 65%
All 16 participating programs were judged on how human-like their responses were to these questions.
Arckon scored 13 of 20 points, ranking 7th, on par with A.L.I.C.E. and Cleverbot (a dubious honour). For moral reasons I did not want Arckon to pretend being a human, so I didn’t program a fictional human background story. Instead I relied on his linguistic and reasoning abilities to find genuine answers, but as you can see this could not compensate the lack of fictional facts that were asked. Surprisingly, Arckon still scored half a point for every “I don’t know” answer just for understanding the question.

Uncommonly common
If you weren’t impressed with Arckon’s responses; Neither was I. But I was equally unimpressed with the unexpectedly ordinary line of questioning. Where all previous years focused on kindergarten-style logic questions like “How much is 5+3?”, “Which is bigger, an apple or a watermelon?”, and various tests of memory, 2013 focused purely on common small talk, with the program (“you”/”your”) always the subject of the question. A curious choice considering even the most basic chatbot –made for small talk- would come equipped with prewritten responses to these. This showed in that the highest score in the qualifying test was achieved by the chatbot with the least development time. Nevertheless the winning chatbot in the finals deservedly won as the most conversational of all entrants.