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.

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?
(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.


2 thoughts on “Turing Test 2016

  1. Hey! I’ve been reading your blog for some time and really enjoy it. Congrats on your score! Do you have any advice for starting out writing a chatbot, especially if my programming experience is in a language that isn’t traditionally used for it? I’m currently working in NLP and chatbots have always fascinated me.


    • Best advice: Join http://www.chatbots.org and introduce yourself on the forum, where all the chatbot creators hang out 😉
      I don’t work with common chatbot scripting languages either, but the ones that are out there are much easier to understand than programming languages. Coming from a C++ and NLP angle, I find ChatScript most familiar and efficient, and it has a built-in grammar parser. To be honest it’s more difficult to get good conversational results with proper NLP and language generation, as opposed to simpler word-matching techniques and scripted answers. The best of both worlds would be to use NLP to get the core of the input right, branch that off to conversational categories/topics (greet, straight question, open question, problem statement, opinion request, etc), and then output pre-composed answers. Personally, I also take a lot of hints from psychology books on human conversation, and I think a lot of chatbot projects could use some of that.


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s