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

A Neural Conversational Model [pdf]

arxiv.org

Post reply on HN
Print view View original

1–10 of 41 posts

Re: A Neural Conversational Model [pdf]

#2

Post by Nadya »

The conversations are rather enlightening.

>What is the color of water? Water.

I'm quite puzzled how it knows "two plus two" is four but "ten minus two" is "seventy-two". I wonder how it parsed one correctly but failed drastically to parse the other.

Re: A Neural Conversational Model [pdf]

#3

Post by biot »

Nadya wrote: post #2

The conversations are rather enlightening. >What is the color of water? Water. I'm quite puzzled how it knows "two plus two" is four but "ten minus two" is "seventy-two". I wonder how it parsed one correctly but failed drastically to parse the other.

It's not parsing the phrase into the tokens "10 - 2" and evaluating that. Rather, a corpus of data was used to train the neural net and, for whatever reason, the answer "seventy-two" was the highest probability output. In all likelihood, it doesn't even register that this is a math question.

Re: A Neural Conversational Model [pdf]

#5

Post by murbard2 »

Nadya wrote: post #2

The conversations are rather enlightening. >What is the color of water? Water. I'm quite puzzled how it knows "two plus two" is four but "ten minus two" is "seventy-two". I wonder how it parsed one correctly but failed drastically to parse the other.

It did not see enough examples to learn a general addition algorithm. "Two plus two equals four" is a common sentence, "Ten minus two equals eight" isn't.

In fact, it's likely that no one learns addition by listening to examples, you're taught to execute a specific algorithm and it takes many people years to master it. In fact, ask a toddler what "ten minus two" is and you might get a similar nonsensical answer.

Re: A Neural Conversational Model [pdf]

#6

Post by Nadya »

murbard2 wrote: post #5
Nadya wrote: post #2

The conversations are rather enlightening. >What is the color of water? Water. I'm quite puzzled how it knows "two plus two" is four but "ten minus two" is "seventy-two". I wonder how it parsed one correctly but failed drastically to parse the other.

It did not see enough examples to learn a general addition algorithm. "Two plus two equals four" is a common sentence, "Ten minus two equals eight" isn't. In fact, it's likely that no one learns addition by listening to examples, you're taught to execute a specific algorithm and it takes many people years to master it. In fact, ask a toddler what "ten minus two" is and you might get a similar nonsensical answer.

I hadn't thought of the "common sentence" approach. Woops.

I was thinking semi-intelligent parsing and it recognized "two" and "plus" and created a formula 2+2 then solved it with 4 ("four").

So I had assumed it would have done the same with "ten", "minus", and "two" to create 10-2, solve it, and respond with 8 ("eight").

If you use Google Search and search for "ten minus two" it's intelligent enough to parse the search and give you a calculator with 10-2=8 already inputted. I had assumed a similar parsing approach may have been used for their conversation bot in regards to general mathematical knowledge.

But your explanation makes a ton of sense. :)

Re: A Neural Conversational Model [pdf]

#9

Post by joelthelion »

feld wrote: post #4

I think this could be successfully trained to walk many people through all kinds of basic support issues... using years of tech support chat logs would probably make this a breeze.

One problem is that when the machine says it's doing something, it's actually not doing anything. The chat logs don't contain information about the actions of the tech.

Re: A Neural Conversational Model [pdf]

#10

Post by hobs »

vasco wrote: post #8

> Machine: hi , this is from helpdesk connect , what can i help you with today ? > Human: hi , i forgot my password > Machine: ok great That's something unexpected to hear from tech support.

When I worked in tech support, I cant tell you how many times I would say "Great! (realize that its not great for them) that we have isolated the issue."
Post reply on HN