Stanza: A Python natural language processing toolkit for many human languages

Re:Stanza: A Python natural language processing toolkit for ... by mylampisawesome on Tuesday March 24, 2020 @04:53PM (#22678898)

I was rather curious to see how this handled Garden Path Sentences[0]. For "The old man the boat.", Stanza interprets "man" as a noun rather than a verb. Similarly, for "The complex houses married and single soldiers and their families." "houses" is also interpreted as a noun rather than a verb. These sentences are mostly corner-cases, but was an interesting little experiment nonetheless.

[0] https://en.wikipedia.org/wiki/Garden-path_sentence

[ Parent | on HN ]

Re:Stanza: A Python natural language processing toolkit for ... by eindiran on Tuesday March 24, 2020 @07:10PM (#22680048)

Most humans struggle when reading garden-path sentences, so I would be quite impressed if an NLP toolkit handled them easily out-of-the-box.

EDIT: On a related note, when I was an undergrad there was a group on campus that was doing research on how humans repair garden-path sentences when their first reading is incorrect. They were measuring ERPs to see if something akin to a backtracking algorithm was used + eye-tracking to see which word/words triggered the repair. I graduated before the work was complete, but I might go digging for it to see if it was ever published.

EDIT 2: Apparently this is better researched than I realized: https://en.wikipedia.org/wiki/P600_(neuroscience)

[ Parent | on HN ]

Re:Stanza: A Python natural language processing toolkit for ... by felixyz on Tuesday March 24, 2020 @07:40PM (#22680255)

Very interesting! Thanks for the link, and if you find out more about the research the group at you uni was doing, please post!

[ Parent | on HN ]

Re:Stanza: A Python natural language processing toolkit for ... by bryanrasmussen on Wednesday March 25, 2020 @05:18AM (#22683060)

I think my eyes always track back when I realize something is wrong in how I have interpreted the sentence.

[ Parent | on HN ]

Re:Stanza: A Python natural language processing toolkit for ... by garmaine on Tuesday March 24, 2020 @11:46PM (#22681776)

I think that's too high a bar. I didn't interpret either one of those sentences the first time I read it either. It would be obtuse to expect even a "human-level" AI to get these right. Though you could fix it to get it right by backtracking to see if there are alternate solutions that generate complete parses.

[ Parent | on HN ]

Re:Stanza: A Python natural language processing toolkit for ... by superpermutat0r on Wednesday March 25, 2020 @07:26AM (#22683590)

But still, this kind of analysis (part-of-speech, dependency parsing, etc.) was deemed useless with NN transformer models.

The solutions to these low-level problems seem to be unimportant for high level tasks. Not to mention that error propagates. Error on part-of-speech tagging will propagate to dependency parsing that uses that info, and eventually this error will affect NER or entity/relationship extraction and similar.

[ Parent | on HN ]