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

Watch a machine-learning system parse the grammatical structure of sentences

foxtype.com

Post reply on HN
Print view View original

21–30 of 32 posts

Re: Watch a machine-learning system parse the grammatical structure of sentences

#21

Post by canjobear »

amirkdv wrote: post #19
meepmorp wrote: post #12

It got "colorless green ideas sleep furiously," wrong.

I don't see how it got it wrong (and it would be surprising if it did given the sentence is not syntactically ambiguous). It does use a visual notation which, AFAIK, differs from the standard in linguistcs [0]. [0]: https://en.wikipedia.org/wiki/File:Syntax_tree_for_Colorless...

This site is producing dependency parses, which have become popular in the last 10 years or so. The linked figure is a phrase structure parse, which used to be the thing everyone worked on but have since turned out to be both harder to get and less useful than dependency parses.

Re: Watch a machine-learning system parse the grammatical structure of sentences

#22

Post by meepmorp »

amirkdv wrote: post #19
meepmorp wrote: post #12

It got "colorless green ideas sleep furiously," wrong.

I don't see how it got it wrong (and it would be surprising if it did given the sentence is not syntactically ambiguous). It does use a visual notation which, AFAIK, differs from the standard in linguistcs [0]. [0]: https://en.wikipedia.org/wiki/File:Syntax_tree_for_Colorless...

It decided that "sleep," was a noun, rather than a verb (as in the diagram you note). If your parts of speech are wrong, it's not a successful parse.

Re: Watch a machine-learning system parse the grammatical structure of sentences

#23

Post by jonathankoren »

nevir wrote: post #17
ma2rten wrote: post #9

Earlier quoted context omitted.

It uses machine learning to parse the sentence, all modern lexical parsers are based on machine learning.

Aren't most of them rule based?

Not for years. State of the art has moved on from Eric Brill's dissertation 25 years ago.

Re: Watch a machine-learning system parse the grammatical structure of sentences

#24

Post by dimdimdim »

loser777 wrote: post #20
Vivtek wrote: post #3

Seems to fall for a lot of easy traps. Garden path sentences ("The old man the boats" or "The horse raced past the barn fell") are parsed wrong, and it parses the two sentences/phrases "When he did that I laughed" and "When he said that I laughed" identically - by interpreting "that" as a preposition in both cases, which it isn't. It's cool that it parses on the fly. But unless it parses correctly I don't see how it…

My favorite is "Fruit flies like honey." which trips this parser up as well.

Type in "Fruit Flies like honey"

Re: Watch a machine-learning system parse the grammatical structure of sentences

#26

Post by yongjik »

mark_element wrote: post #25

It doesn't do well on the classic: https://en.wikipedia.org/wiki/Buffalo_buffalo_Buffalo_buffal...

To be fair, if someone actually utters that sentence, I think most English speakers would reply with "I'm sorry?" or "Do you need help?"

Re: Watch a machine-learning system parse the grammatical structure of sentences

#27

Post by DonaldFisk »

Vivtek wrote: post #3

Seems to fall for a lot of easy traps. Garden path sentences ("The old man the boats" or "The horse raced past the barn fell") are parsed wrong, and it parses the two sentences/phrases "When he did that I laughed" and "When he said that I laughed" identically - by interpreting "that" as a preposition in both cases, which it isn't. It's cool that it parses on the fly. But unless it parses correctly I don't see how it…

These require a system which either backtracks or recognizes it's made a mistake and corrects it. I know how to do that with a rule-based parser.

It also fails on "British left waffles on Falklands." While there are two syntactic parsers for that, one of them borders on the absurd and should be rejected. The problem is that to parse some sentences requires understanding of the words and phrases it reads, which in turn requires common sense.

Re: Watch a machine-learning system parse the grammatical structure of sentences

#28

Post by DonaldFisk »

dimdimdim wrote: post #24
loser777 wrote: post #20

Earlier quoted context omitted.

My favorite is "Fruit flies like honey." which trips this parser up as well.

Type in "Fruit Flies like honey"

So, to get correct output, you need to give it incorrect input? You don't capitalize names of animal or plant species in English.

Re: Watch a machine-learning system parse the grammatical structure of sentences

#29

Post by Borating »

yongjik wrote: post #26
mark_element wrote: post #25

It doesn't do well on the classic: https://en.wikipedia.org/wiki/Buffalo_buffalo_Buffalo_buffal...

To be fair, if someone actually utters that sentence, I think most English speakers would reply with "I'm sorry?" or "Do you need help?"

See the video TED-Ed Buffalo buffalo buffalo: One-word sentences and how they work - Emma Bryce [1]

[1] https://www.youtube.com/watch?v=TWbzjGIec20

Post reply on HN