Matches in SemOpenAlex for { <https://semopenalex.org/work/W2919000501> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2919000501 endingPage "685" @default.
- W2919000501 startingPage "667" @default.
- W2919000501 abstract "We introduce a novel framework for delexicalized dependency parsing in a new language. We show that useful features of the target language can be extracted automatically from an unparsed corpus, which consists only of gold part-of-speech (POS) sequences. Providing these features to our neural parser enables it to parse sequences like those in the corpus. Strikingly, our system has no supervision in the target language. Rather, it is a multilingual system that is trained end-to-end on a variety of other languages, so it learns a feature extractor that works well. We show experimentally across multiple languages: (1) Features computed from the unparsed corpus improve parsing accuracy. (2) Including thousands of synthetic languages in the training yields further improvement. (3) Despite being computed from unparsed corpora, our learned task-specific features beat previous work’s interpretable typological features that require parsed corpora or expert categorization of the language. Our best method improved attachment scores on held-out test languages by an average of 5.6 percentage points over past work that does not inspect the unparsed data (McDonald et al., 2011), and by 20.7 points over past “grammar induction” work that does not use training languages (Naseem et al., 2010)." @default.
- W2919000501 created "2019-03-11" @default.
- W2919000501 creator A5043674345 @default.
- W2919000501 creator A5052467896 @default.
- W2919000501 date "2018-12-01" @default.
- W2919000501 modified "2023-09-23" @default.
- W2919000501 title "Surface Statistics of an Unknown Language Indicate How to Parse It" @default.
- W2919000501 cites W2494423583 @default.
- W2919000501 doi "https://doi.org/10.1162/tacl_a_00248" @default.
- W2919000501 hasPublicationYear "2018" @default.
- W2919000501 type Work @default.
- W2919000501 sameAs 2919000501 @default.
- W2919000501 citedByCount "21" @default.
- W2919000501 countsByYear W29190005012018 @default.
- W2919000501 countsByYear W29190005012019 @default.
- W2919000501 countsByYear W29190005012020 @default.
- W2919000501 countsByYear W29190005012021 @default.
- W2919000501 crossrefType "journal-article" @default.
- W2919000501 hasAuthorship W2919000501A5043674345 @default.
- W2919000501 hasAuthorship W2919000501A5052467896 @default.
- W2919000501 hasBestOaLocation W29190005011 @default.
- W2919000501 hasConcept C117978034 @default.
- W2919000501 hasConcept C127413603 @default.
- W2919000501 hasConcept C136197465 @default.
- W2919000501 hasConcept C138885662 @default.
- W2919000501 hasConcept C154945302 @default.
- W2919000501 hasConcept C164883195 @default.
- W2919000501 hasConcept C186644900 @default.
- W2919000501 hasConcept C204321447 @default.
- W2919000501 hasConcept C21880701 @default.
- W2919000501 hasConcept C26022165 @default.
- W2919000501 hasConcept C2776401178 @default.
- W2919000501 hasConcept C41008148 @default.
- W2919000501 hasConcept C41895202 @default.
- W2919000501 hasConcept C94124525 @default.
- W2919000501 hasConceptScore W2919000501C117978034 @default.
- W2919000501 hasConceptScore W2919000501C127413603 @default.
- W2919000501 hasConceptScore W2919000501C136197465 @default.
- W2919000501 hasConceptScore W2919000501C138885662 @default.
- W2919000501 hasConceptScore W2919000501C154945302 @default.
- W2919000501 hasConceptScore W2919000501C164883195 @default.
- W2919000501 hasConceptScore W2919000501C186644900 @default.
- W2919000501 hasConceptScore W2919000501C204321447 @default.
- W2919000501 hasConceptScore W2919000501C21880701 @default.
- W2919000501 hasConceptScore W2919000501C26022165 @default.
- W2919000501 hasConceptScore W2919000501C2776401178 @default.
- W2919000501 hasConceptScore W2919000501C41008148 @default.
- W2919000501 hasConceptScore W2919000501C41895202 @default.
- W2919000501 hasConceptScore W2919000501C94124525 @default.
- W2919000501 hasLocation W29190005011 @default.
- W2919000501 hasOpenAccess W2919000501 @default.
- W2919000501 hasPrimaryLocation W29190005011 @default.
- W2919000501 hasRelatedWork W1592893681 @default.
- W2919000501 hasRelatedWork W1837762017 @default.
- W2919000501 hasRelatedWork W2020540721 @default.
- W2919000501 hasRelatedWork W2022928063 @default.
- W2919000501 hasRelatedWork W2200456380 @default.
- W2919000501 hasRelatedWork W2250415202 @default.
- W2919000501 hasRelatedWork W2293457016 @default.
- W2919000501 hasRelatedWork W2511797247 @default.
- W2919000501 hasRelatedWork W2559370752 @default.
- W2919000501 hasRelatedWork W2952345041 @default.
- W2919000501 hasVolume "6" @default.
- W2919000501 isParatext "false" @default.
- W2919000501 isRetracted "false" @default.
- W2919000501 magId "2919000501" @default.
- W2919000501 workType "article" @default.