AI Zone Admin Forum Add your forum

NEWS: Chatbots.org survey on 3000 US and UK consumers shows it is time for chatbot integration in customer service!read more..

The 2014 Loebner
 
 

OK, I am curious. Who entered this years Loebner?

 

 
  [ # 1 ]

These are the ones I know about in no particular order:

Steve Worswick
Dr Richard Wallace
Adeena Mignogna
Ron Lee
Brian Rigsby
Peter Lafferty
Merlin
Tom Joyce
Denis Robert
Don Patrick
James Adams
Daniel Burke

I would also hazard a guess that Bruce Wilcox, Will Rayer and Rollo Carpenter have submitted entries too.

However, the AISB site hasn’t been updated, so my guesses may be wrong (I would be surprised if Bruce hasn’t entered though).

 

 
  [ # 2 ]

Hi Steve,

did you change much to your entry this year? I noticed you updated the graphics on the Mitsuku website.


Dan

 

 
  [ # 3 ]

I felt I had to change the artwork as a lot of women in AI were finding her half naked image offensive so I commisioned a more mature design.

As for the bot itself, I’ve not really made any major changes apart from checking the chatlogs and improving/adding responses based on what people have been asking her. She has been busy since winning last year and so I’ve added just over 20,000 new categories to her plus another couple of hundred objects where she can query colour, size etc. for the old favourites of “is x larger than y?” type questions.

Mistuku should be able to handle the Loebner Prize templates but there are lots of good entries in the contest and so just getting to the final 4 will be a great acheivement for whoever make it.

 

 
  [ # 4 ]

That makes sense, best not encourage too much dirty talk. It doesn’t help develop the bot.

The bots do seem to be getting better each year. It becomes harder and harder to get into the top four.

My own bot has had a “bit” of a memory transplant so I am hoping it performs better than last year.

Good luck with your entry.

Dan

 

 

 
  [ # 5 ]

You too Dan and indeed everyone who has entered.

 

 
  [ # 6 ]

Hi All,

I ran across this letter to the editors of Salon.com, by Hugh Loebner just after “the fiasco of 2002” in Atlanta.  The 2002 Loebner prize contest, for those who weren’t around then, was an incredible kerfuffle*, credited to me on the internet by my then employer, Neil Bishop, who insisted that I have no dealings with the contest because I would be “prejudiced.” Given that I was the only person involved who knew anything about the contest, Hugh never seemed to blame me for it. We met for lunch together in Atlanta in July, a few months before the contest. The subject was never breached. Instead, Hugh gave me a copy of his patent for a method of giving a tip to the waiter at a restaurant. (I still have it.)

He seemed to revel in the controversy that resulted from the mismanagement of the contest, and the fact that a Salon writer wrote about him. Puzzled the hell out of me for years, and then I met him in 2005, at the Guilford colloquium in 2005. We had breakfast together, and met later for (lunch?) dinner. He was gracious, and entertaining. The subject of 2002 never came up, thankfully to me, and I gained respect for him in an odd, Father Ted, sort of way.

In 2003, he wrote a letter to Salon.com which they published. In it, he said, “To those readers who claim that the Turing Test is not a good measure of intelligence I would reply that it is one measure of intelligence. I have no objections, philosophical, moral, or personal to other measures or tests. It is just that I have an interest in the Turing Test, not the other tests. If the Turing Test shows an entity to be “intelligent” but the others don’t, or vice versa, we may have a problem. On the other hand, I think it likely that any computer entity that passes a Turing Test will likely do quite well on other measures of intelligence also. It will be interesting to see if this is so.

To those readers who claim that the Turing Test is a valid measure of intelligence, but that the Loebner Prize contest is not a good Turing Test, I ask “why not?” In what manner is the Loebner Prize contest, as currently held, different from the exercise that Turing described? Note that the horrible rule that conversations have to be restricted has been removed.” - Hugh Loebner, Letter to Salon.com, 2003.

I join our fellows in anxiously waiting to hear about the finalists for 2014 at Bletchley.

Robby.

* Sorry, Robby. Had to do a minor edit - Dave

 

 
  [ # 7 ]

H all,


I am a newcomer to the Loebner contest.
I am very eager to see the selection results to be announced this week!


Looking at the increasing quality in programs, being selected is a feat in itself, so in advance I want to congratulate all contestants.


Chatbots.org looks like a very welcoming community - this deserves some great respect. I can say that it is great to see that most of you seem to know each other!

In reaction to Robby’s post:

I am so new I would not know details of Loebner’s past.
But to speak about what it may entail:

Loebner contest inspires great things and great motives.
This helps people getting better at making something better.
Who, or what can say as much?  wink


In my case, this is one of the main elements in life which made me focus efforts on conversational AI. Loebner contest is giving us fuel for our thinking engines. This creates motion,and progress in itself.

 

 

 
  [ # 8 ]

Great going Christophe!  Never give up! The journey is worth as much as the destination!

Regards,

Robby.

 

 
  [ # 9 ]

Hi Dave,

I bet you’re a “Little Britain” fan.

Robby.

 

 
  [ # 10 ]
Robby Garner - Sep 25, 2014:

Hi Dave,

I bet you’re a “Little Britain” fan.

Robby.

I quite possible could be, if I knew what “Little Brittain” was. :-\

I don’t like having to edit posts, and I’m not quite the prude that I seem to be, here (I use far worse language than that when I’m not immersed in a “family environment”, and have even been known to gratuitously use the word “Belgium”* in my conversations from time to time), but here I have to be a bit more “strict” than I prefer. downer

 


*Hitchhiker’s Guide reference cheese

 

 
  login or register to react