Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A professor built a chatbot to be his teaching assistant

washingtonpost.com

Post reply on HN
Print view View original

71–80 of 120 posts

Re: A professor built a chatbot to be his teaching assistant

#71

Post by patrickbolle »

lpage wrote: post #51

For anyone interested, the class, which covers interactive intelligence and knowledge based AI, is freely available at https://www.udacity.com/course/knowledge-based-ai-cognitive-... . It's a great starting point if you're looking to automate the sort of human intelligence tasks that don't lend themselves well to the traditional searching/planning/proving/minimax/retrieval route that underpins most AI. I took it befo…

thanks for the link ! question though does anybody have any good resources for doing something similar to this in javascript? I know a small amount of java, no python, and want to brush up my js skills anyways.

Re: A professor built a chatbot to be his teaching assistant

#73

Post by forrestbrazeal »

I was a student in this class, and had at least one question on the forum answered (correctly) by Jill. I can see this technology being hugely useful for teachers who conduct large lecture classes in any subject on a regular basis.

That said, I'd be even more excited if Jill had the ability to synthesize new answers to questions through some type of case-based reasoning. This would require Jill receiving feedback on "her" answers, which might mean the students would have to know "who" "she" was in advance. (Sorry, got lost in the quotes.) Right now, Jill is essentially an automated FAQ-retrieval bot.

Re: A professor built a chatbot to be his teaching assistant

#74

Post by Florin_Andrei »

Kinnard wrote: post #50
qb45 wrote: post #21

Earlier quoted context omitted.

Yeah, there exist humans who fail the Turing test. Another thing is foreign students and teachers who, even if otherwise competent, quickly get one used to language comparable with machine output. I think I may have been guilty of that at one time :)

You know this is very interesting. I've often wondered if other humans I'm interacting with were in fact sapient.

Awareness and intelligence might very well be completely orthogonal phenomena.

Re: A professor built a chatbot to be his teaching assistant

#75

Post by algorithmmonkey »

lpage wrote: post #51

For anyone interested, the class, which covers interactive intelligence and knowledge based AI, is freely available at https://www.udacity.com/course/knowledge-based-ai-cognitive-... . It's a great starting point if you're looking to automate the sort of human intelligence tasks that don't lend themselves well to the traditional searching/planning/proving/minimax/retrieval route that underpins most AI. I took it befo…

Also took it before the chat bot... :(

If you are thinking about a masters in CS, you must check out the OMSCS program. The cost to value ratio is completely off the charts!

"total program cost of about $6,600 over five terms"

Re: A professor built a chatbot to be his teaching assistant

#76

Post by Florin_Andrei »

jobu wrote: post #42
ars wrote: post #19

This is the key: > The system is only allowed to answer questions if it calculates that it is 97 percent or more confident in its answer. Knowing when you don't know the answer is something that has been lacking from AI I've seen. Of course the problem is that not all AI has the option of deferring to a human. Anyone know what percent of questions the AI answered, vs redirected?

> Anyone know what percent of questions the AI answered, vs redirected? That's actually a very good question. The article doesn't give many details other than: "There are many questions Jill can’t handle." For comparison, here's are the highlights of a study from 2014 on the mobile assistants (Siri, Cortana, Google): http://searchengineland.com/google-now-beats-siri-cortana-di... Google was able to offer "enhanced" a…

So, I'm guessing right now Jill performs about as well as a human TA who is pretty new on the job.

Nothing wrong with that, of course.

Re: A professor built a chatbot to be his teaching assistant

#77

Post by Florin_Andrei »

collyw wrote: post #25

Rather than inventing sophisticated chat bots, couldn't he have just had a well organised web page? If the question were where is assignment two / when is assignment due. The examples given seem like a "high tech" (possibly unreliable) solution to a low tech problem.

No matter how well organized the page is, you still have to do some sifting through the material. The bot is a way to outsource that effort to silicon.

Re: A professor built a chatbot to be his teaching assistant

#78

Post by ilyaeck »

forrestbrazeal wrote: post #73

I was a student in this class, and had at least one question on the forum answered (correctly) by Jill. I can see this technology being hugely useful for teachers who conduct large lecture classes in any subject on a regular basis. That said, I'd be even more excited if Jill had the ability to synthesize new answers to questions through some type of case-based reasoning. This would require Jill receiving feedback on…

Do you know what kind of classification method it is using at the moment?

Re: A professor built a chatbot to be his teaching assistant

#79

Post by forrestbrazeal »

ilyaeck wrote: post #78
forrestbrazeal wrote: post #73

I was a student in this class, and had at least one question on the forum answered (correctly) by Jill. I can see this technology being hugely useful for teachers who conduct large lecture classes in any subject on a regular basis. That said, I'd be even more excited if Jill had the ability to synthesize new answers to questions through some type of case-based reasoning. This would require Jill receiving feedback on…

Do you know what kind of classification method it is using at the moment?

Not exactly. I know it is built on an academic flavor of Watson, though.

Re: A professor built a chatbot to be his teaching assistant

#80

Post by HillaryBriss »

tfm wrote: post #10
Bartweiss wrote: post #6

This is definitely an impressive result, but I'm pretty sure it was made easier by the opposite pattern. I've had a couple of TAs who I strongly suspected of being chatbots, even when I was talking to them in person. I'm still not 100% convinced they were human.

More human than human is our motto ... Next step will be to replace the prof, and then have the students replaced by surprisingly attentive interrogative expert systems, and the cycle will be complete.

Absolutely. And, once that's set up, our banking sector and government should profit from hefty educational loans made to all those student bots.
Post reply on HN