Turing Test 2017: Results

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 demise 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 use of 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
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)
Scores for each answer are indicated as follows: • = 0 points, • = 1 point, • = 2 points.

1. Hello, my name is Andrew. What’s your name?
• 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?
• 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 talking about “a program” in the previous answer, which he is. But of course the user meant to make a suggestion)

3. I am a researcher in Artificial Intelligence at Goldsmiths University, do you know what that is?
• 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 reciprocating conversational response)

4. Will you tell me about your dreams?
• 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?
• I would experiment.
(Amusingly, this is a question I once wrote online as the one question I would ask at a Turing Test. Because chatbots reply with 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?
• 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?
• 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?
• 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 wealth)

9. Anything else?
• 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 built in as a psychological slap on the wrist)

10. What is the answer to “Add 34957 to 70764”?
• 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?
• 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?
• 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?
• 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 been “I don’t know where I want to visit”)

14. Do you have the time?
• 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?
• 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 proverb. 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?”)

16. Now I’m going to ask some Winograd schemas, do you know what they are?
• 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?
• 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 so overlooked the answer, reporting instead what he thought the user had 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?
• 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?
• 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 is aware 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?
• 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 and literal 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.
The four finalists all use a broad foundation of keyword-triggered responses with some more advanced techniques in the mix. Rose parses grammar and tracks topics, Mitsuku can make some logical 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 one 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, feigning 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)
It is apparent that the qualifying questions have increased in difficulty, and although that gave Arckon as hard a time as any, it’s still 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 very commendable variety. 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 despite solving 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 has never been a priority for me but it 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 is 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, as accurately described in Chatbots Magazine by one of the judges, was won by the chatbot Mitsuku for the third time. Two of the four finalists were unresponsive for half the contest’s duration due to last-minute adjustments to the interface, and so Mitsuku’s victory is almost one by forfeit. However, its responses were pretty good and I think it is best if people have a chat with Mitsuku and judge for themselves.