Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964091096> ?p ?o ?g. }
- W2964091096 abstract "Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a new model that represents complex lexical features---comprised of parts for words, contextual information and labels---in a tensor that captures conjunction information among these parts. We apply low-rank tensor approximations to the corresponding parameter tensors to reduce the parameter space and improve prediction speed. Furthermore, we investigate two methods for handling features that include $n$-grams of mixed lengths. Our model achieves state-of-the-art results on tasks in relation extraction, PP-attachment, and preposition disambiguation." @default.
- W2964091096 created "2019-07-30" @default.
- W2964091096 creator A5024437840 @default.
- W2964091096 creator A5027142928 @default.
- W2964091096 creator A5061241015 @default.
- W2964091096 creator A5063457506 @default.
- W2964091096 date "2016-01-01" @default.
- W2964091096 modified "2023-10-14" @default.
- W2964091096 title "Embedding Lexical Features via Low-Rank Tensors" @default.
- W2964091096 cites W100623710 @default.
- W2964091096 cites W130850236 @default.
- W2964091096 cites W1889268436 @default.
- W2964091096 cites W1984052055 @default.
- W2964091096 cites W2024165284 @default.
- W2964091096 cites W2025768430 @default.
- W2964091096 cites W2053238041 @default.
- W2964091096 cites W2107620532 @default.
- W2964091096 cites W2124012968 @default.
- W2964091096 cites W2125553157 @default.
- W2964091096 cites W2125573226 @default.
- W2964091096 cites W2125972432 @default.
- W2964091096 cites W2128634885 @default.
- W2964091096 cites W2130903752 @default.
- W2964091096 cites W2132529109 @default.
- W2964091096 cites W2133280805 @default.
- W2964091096 cites W2136502946 @default.
- W2964091096 cites W2146502635 @default.
- W2964091096 cites W2147022480 @default.
- W2964091096 cites W2153579005 @default.
- W2964091096 cites W2158139315 @default.
- W2964091096 cites W2158899491 @default.
- W2964091096 cites W2163568299 @default.
- W2964091096 cites W2168963845 @default.
- W2964091096 cites W2172099713 @default.
- W2964091096 cites W2175392422 @default.
- W2964091096 cites W2250324053 @default.
- W2964091096 cites W2250861254 @default.
- W2964091096 cites W2251837567 @default.
- W2964091096 cites W2251939518 @default.
- W2964091096 cites W2293958133 @default.
- W2964091096 cites W2295528990 @default.
- W2964091096 cites W2951131188 @default.
- W2964091096 cites W2962722345 @default.
- W2964091096 cites W2962755455 @default.
- W2964091096 cites W2963171262 @default.
- W2964091096 cites W2964349647 @default.
- W2964091096 cites W68132019 @default.
- W2964091096 doi "https://doi.org/10.18653/v1/n16-1117" @default.
- W2964091096 hasPublicationYear "2016" @default.
- W2964091096 type Work @default.
- W2964091096 sameAs 2964091096 @default.
- W2964091096 citedByCount "3" @default.
- W2964091096 countsByYear W29640910962018 @default.
- W2964091096 countsByYear W29640910962021 @default.
- W2964091096 crossrefType "proceedings-article" @default.
- W2964091096 hasAuthorship W2964091096A5024437840 @default.
- W2964091096 hasAuthorship W2964091096A5027142928 @default.
- W2964091096 hasAuthorship W2964091096A5061241015 @default.
- W2964091096 hasAuthorship W2964091096A5063457506 @default.
- W2964091096 hasBestOaLocation W29640910961 @default.
- W2964091096 hasConcept C111919701 @default.
- W2964091096 hasConcept C114614502 @default.
- W2964091096 hasConcept C153180895 @default.
- W2964091096 hasConcept C154945302 @default.
- W2964091096 hasConcept C155281189 @default.
- W2964091096 hasConcept C164226766 @default.
- W2964091096 hasConcept C202444582 @default.
- W2964091096 hasConcept C204321447 @default.
- W2964091096 hasConcept C2524010 @default.
- W2964091096 hasConcept C2777462759 @default.
- W2964091096 hasConcept C2778572836 @default.
- W2964091096 hasConcept C33923547 @default.
- W2964091096 hasConcept C41008148 @default.
- W2964091096 hasConcept C41608201 @default.
- W2964091096 hasConcept C90805587 @default.
- W2964091096 hasConceptScore W2964091096C111919701 @default.
- W2964091096 hasConceptScore W2964091096C114614502 @default.
- W2964091096 hasConceptScore W2964091096C153180895 @default.
- W2964091096 hasConceptScore W2964091096C154945302 @default.
- W2964091096 hasConceptScore W2964091096C155281189 @default.
- W2964091096 hasConceptScore W2964091096C164226766 @default.
- W2964091096 hasConceptScore W2964091096C202444582 @default.
- W2964091096 hasConceptScore W2964091096C204321447 @default.
- W2964091096 hasConceptScore W2964091096C2524010 @default.
- W2964091096 hasConceptScore W2964091096C2777462759 @default.
- W2964091096 hasConceptScore W2964091096C2778572836 @default.
- W2964091096 hasConceptScore W2964091096C33923547 @default.
- W2964091096 hasConceptScore W2964091096C41008148 @default.
- W2964091096 hasConceptScore W2964091096C41608201 @default.
- W2964091096 hasConceptScore W2964091096C90805587 @default.
- W2964091096 hasLocation W29640910961 @default.
- W2964091096 hasLocation W29640910962 @default.
- W2964091096 hasOpenAccess W2964091096 @default.
- W2964091096 hasPrimaryLocation W29640910961 @default.
- W2964091096 hasRelatedWork W133480135 @default.
- W2964091096 hasRelatedWork W2335882425 @default.
- W2964091096 hasRelatedWork W2567035470 @default.
- W2964091096 hasRelatedWork W2949267551 @default.
- W2964091096 hasRelatedWork W2993300079 @default.
- W2964091096 hasRelatedWork W3086845375 @default.