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

How to Get into Natural Language Processing

blog.ycombinator.com

Post reply on HN
Print view View original

31–40 of 80 posts

Re: How to Get into Natural Language Processing

#31

Post by ice109 »

chch wrote: post #24
d_burfoot wrote: post #14

> Why is NLP Hard? ... Language is highly ambiguous - it relies on subtle cues and contexts to convey meaning. This is true, but it is only part of the answer. Another part of the answer is what I call the Long Tail of Grammar. It turns out that if you try to write down all the rules of grammar, you will not get 40 or 60 rules, but something more like 100s or maybe even 1000s of rules. Most of those rules are obscure…

> or useable only in specific contexts or with specific words. A good example of this is the Winograd Schema. You might think you can figure out a good algorithm for anaphoric resolution (i.e. If you see "Sally called and she said hello.", who is "she"?) that just relies on the structure of a sentence, without considering semantics. But here's a counterexample: "The city councilmen refused the demonstrators a permit…

re the council people sentences: I don't understand the problem. they're ill-defined sentences. we use heuristics to parse them but those heuristics can fail (the council denied the demonstrators permit because they feared violence... and the council was obliging). just teach the computer the heuristics like we learn them.

Re: How to Get into Natural Language Processing

#33

Post by chch »

ice109 wrote: post #31
chch wrote: post #24

Earlier quoted context omitted.

> or useable only in specific contexts or with specific words. A good example of this is the Winograd Schema. You might think you can figure out a good algorithm for anaphoric resolution (i.e. If you see "Sally called and she said hello.", who is "she"?) that just relies on the structure of a sentence, without considering semantics. But here's a counterexample: "The city councilmen refused the demonstrators a permit…

re the council people sentences: I don't understand the problem. they're ill-defined sentences. we use heuristics to parse them but those heuristics can fail (the council denied the demonstrators permit because they feared violence... and the council was obliging). just teach the computer the heuristics like we learn them.

That's exactly the issue. The way we learn them is through world experience, which is sometimes hard to figure out how to transfer into a computer.

Example:

"I dropped the egg on my glass living room table and it broke!"

"I dropped my hammer on my glass living room table and it broke!"

These are both ill-defined semantically, but if you asked most native English speakers "what broke" for each sentence, they'd probably say "egg" for the first and "table" for the second. It could be the other, but it would be surprising. So, to solve just the "Dropped X on Y, Z broke" problem, we'd need to teach the computer to understand the effect of the relative 'fragility scores' of each object. Personally, I never sat down and memorized a chart of these as a human. You could perhaps use machine learning to derive the data by analyzing a large corpus of text[1], and match humans most of the time, but then that's just one sentence type solved, out of any number of other tricky constructions. So the long tail of semantic understanding quickly becomes a very fun set of problems to solve, for certain definitions of fun. :)

A few more examples to consider how you would teach a computer to understand, from a Winograd Schema corpus[2]:

John couldn't see the stage with Billy in front of him because he is so [short/tall]. Who is so [short/tall]?

The sculpture rolled off the shelf because it wasn't [anchored/level]. What wasn't [anchored/level]?

The older students were bullying the younger ones, so we [rescued/punished] them. Whom did we [rescue/punish]?

I tried to paint a picture of an orchard, with lemons in the lemon trees, but they came out looking more like [light bulbs / telephone poles]. What looked like [light bulbs / telephone poles]?

[1] e.g. http://cs.rochester.edu/research/lore/

[2] http://www.cs.nyu.edu/faculty/davise/papers/WinogradSchemas/...

Re: How to Get into Natural Language Processing

#34

Post by argonaut »

d_burfoot wrote: post #14

> Why is NLP Hard? ... Language is highly ambiguous - it relies on subtle cues and contexts to convey meaning. This is true, but it is only part of the answer. Another part of the answer is what I call the Long Tail of Grammar. It turns out that if you try to write down all the rules of grammar, you will not get 40 or 60 rules, but something more like 100s or maybe even 1000s of rules. Most of those rules are obscure…

Your example isn't even a specific grammar rule. It's a very broad language rule, which is: "descriptions should conform to the real world."

Someone who has never seen a peach might assume that hairy peeled peach refers to a hairy peach without a peel. If you've seen a peach before, this makes no sense. So the assumption is that the peach has a hairy peel.

This is why purely statistical / supervised learning-based NLP alone is not enough.

Re: How to Get into Natural Language Processing

#37

Post by throwaway91111 »

d_burfoot wrote: post #14

> Why is NLP Hard? ... Language is highly ambiguous - it relies on subtle cues and contexts to convey meaning. This is true, but it is only part of the answer. Another part of the answer is what I call the Long Tail of Grammar. It turns out that if you try to write down all the rules of grammar, you will not get 40 or 60 rules, but something more like 100s or maybe even 1000s of rules. Most of those rules are obscure…

This seems like a great argument for automatic grammar learning. How far has current research taken us in that direction?

I'd much rather feed it edge cases to accommodate than rules to follow.

Re: How to Get into Natural Language Processing

#39

Post by Eridrus »

chch wrote: post #33
ice109 wrote: post #31

Earlier quoted context omitted.

re the council people sentences: I don't understand the problem. they're ill-defined sentences. we use heuristics to parse them but those heuristics can fail (the council denied the demonstrators permit because they feared violence... and the council was obliging). just teach the computer the heuristics like we learn them.

That's exactly the issue. The way we learn them is through world experience, which is sometimes hard to figure out how to transfer into a computer. Example: "I dropped the egg on my glass living room table and it broke!" "I dropped my hammer on my glass living room table and it broke!" These are both ill-defined semantically, but if you asked most native English speakers "what broke" for each sentence, they'd probabl…

That's pretty cool. I wonder if the recent work on caption generation mixed with video understanding can get some sense of likelihood of disambiguated sentences to evaluate possible hypotheses.

Re: How to Get into Natural Language Processing

#40

Post by hiddencost »

throwaway91111 wrote: post #37
d_burfoot wrote: post #14

> Why is NLP Hard? ... Language is highly ambiguous - it relies on subtle cues and contexts to convey meaning. This is true, but it is only part of the answer. Another part of the answer is what I call the Long Tail of Grammar. It turns out that if you try to write down all the rules of grammar, you will not get 40 or 60 rules, but something more like 100s or maybe even 1000s of rules. Most of those rules are obscure…

This seems like a great argument for automatic grammar learning. How far has current research taken us in that direction? I'd much rather feed it edge cases to accommodate than rules to follow.

They tried that in the 70s and 80s until they realized they were wasting their time. Probabilistic context free grammars were a thing, also.

Long story short, there's no such thing as grammar but they're a nice fiction for talking about communication. The deeper you get into NLP the more you (1) see what jelinek was talking about when he said "every time I fire a linguist, accuracy goes up" (he was hiring physicists and information theorists), and (2) realize that basically every thought, belief, and statement is deeply ambiguous, and that most human communication is ad hoc.

Also, the more time you spend looking at live data from users, the more you realize that the notion of language as a generally shared system of meaning is not real. Trivial communication about basic tasks is doable, although you often will fuck up there too when talking to someone with deeply different cultural expectations.

If you think that _any_ sentence has unambiguous meaning, you should try to meet some people who are more different than you are. Or get into deeper conversations with the people you know.

Edit: typo

Post reply on HN