Chuckling a Bit at Microsoft and the PCFG Formalism

post by Daniel_Burfoot · 2017-03-20T19:37:38.733Z · score: 5 (6 votes) · LW · GW · Legacy · 3 comments

This is a link post for


Comments sorted by top scores.

comment by dogiv · 2017-03-20T20:43:50.392Z · score: 2 (2 votes) · LW · GW

Interesting piece. It seems like coming up with a good human-checkable way to evaluate parsing is pretty fundamental to the problem. You may have noticed already, but Ozora is the only one that didn't figure out "easily" goes with "parse".

comment by Daniel_Burfoot · 2017-03-20T21:11:37.585Z · score: 0 (0 votes) · LW · GW

Good catch. Adverbial attachment is really hard, because there aren't a lot of rules about where adverbs can go.

Actually, Ozora's parse has another small problem, which is that it interprets "complex" as an NN with a "typeadj" link, instead of as a JJ with an "adject" link. The typeadj link is used for noun-noun pairings such as "police officer", "housing crisis", or "oak tree".

For words that can function as both NN and JJ (eg "complex"), it is quite hard to disambiguate the two patterns.

comment by Douglas_Knight · 2017-03-20T23:52:02.892Z · score: 0 (0 votes) · LW · GW

Some things are really hard, but if everyone else can get this adverb correct, maybe it isn't that hard.