Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964296073> ?p ?o ?g. }
- W2964296073 abstract "We consider the supervised training setting in which we learn task-specific word embeddings. We assume that we start with initial embeddings learned from unlabelled data and update them to learn taskspecific embeddings for words in the supervised training data. However, for new words in the test set, we must use either their initial embeddings or a single unknown embedding, which often leads to errors. We address this by learning a neural network to map from initial embeddings to the task-specific embedding space, via a multi-loss objective function. The technique is general, but here we demonstrate its use for improved dependency parsing (especially for sentences with out-of-vocabulary words), as well as for downstream improvements on sentiment analysis." @default.
- W2964296073 created "2019-07-30" @default.
- W2964296073 creator A5001987532 @default.
- W2964296073 creator A5015602781 @default.
- W2964296073 creator A5055155740 @default.
- W2964296073 creator A5081022650 @default.
- W2964296073 date "2016-01-01" @default.
- W2964296073 modified "2023-09-26" @default.
- W2964296073 title "Mapping Unseen Words to Task-Trained Embedding Spaces" @default.
- W2964296073 cites W1505680913 @default.
- W2964296073 cites W1586073462 @default.
- W2964296073 cites W1614298861 @default.
- W2964296073 cites W1632114991 @default.
- W2964296073 cites W175570475 @default.
- W2964296073 cites W1832693441 @default.
- W2964296073 cites W1859633635 @default.
- W2964296073 cites W1860935423 @default.
- W2964296073 cites W1883682364 @default.
- W2964296073 cites W1889584887 @default.
- W2964296073 cites W1899794420 @default.
- W2964296073 cites W1973346430 @default.
- W2964296073 cites W2051434435 @default.
- W2964296073 cites W2095705004 @default.
- W2964296073 cites W2100664567 @default.
- W2964296073 cites W2102017903 @default.
- W2964296073 cites W2105103433 @default.
- W2964296073 cites W2112628236 @default.
- W2964296073 cites W2112688502 @default.
- W2964296073 cites W2118434577 @default.
- W2964296073 cites W2120615054 @default.
- W2964296073 cites W2124206172 @default.
- W2964296073 cites W2124416056 @default.
- W2964296073 cites W2132890663 @default.
- W2964296073 cites W2155157567 @default.
- W2964296073 cites W2158139315 @default.
- W2964296073 cites W2158899491 @default.
- W2964296073 cites W2187089797 @default.
- W2964296073 cites W2189472871 @default.
- W2964296073 cites W2250303366 @default.
- W2964296073 cites W2250491963 @default.
- W2964296073 cites W2250539671 @default.
- W2964296073 cites W2250861254 @default.
- W2964296073 cites W2251012068 @default.
- W2964296073 cites W2251874715 @default.
- W2964296073 cites W2251939518 @default.
- W2964296073 cites W2262099980 @default.
- W2964296073 cites W2949563612 @default.
- W2964296073 cites W2949952998 @default.
- W2964296073 cites W2950726992 @default.
- W2964296073 cites W2963355447 @default.
- W2964296073 cites W55657863 @default.
- W2964296073 cites W655994999 @default.
- W2964296073 doi "https://doi.org/10.18653/v1/w16-1612" @default.
- W2964296073 hasPublicationYear "2016" @default.
- W2964296073 type Work @default.
- W2964296073 sameAs 2964296073 @default.
- W2964296073 citedByCount "10" @default.
- W2964296073 countsByYear W29642960732017 @default.
- W2964296073 countsByYear W29642960732018 @default.
- W2964296073 countsByYear W29642960732019 @default.
- W2964296073 countsByYear W29642960732020 @default.
- W2964296073 countsByYear W29642960732021 @default.
- W2964296073 countsByYear W29642960732022 @default.
- W2964296073 crossrefType "proceedings-article" @default.
- W2964296073 hasAuthorship W2964296073A5001987532 @default.
- W2964296073 hasAuthorship W2964296073A5015602781 @default.
- W2964296073 hasAuthorship W2964296073A5055155740 @default.
- W2964296073 hasAuthorship W2964296073A5081022650 @default.
- W2964296073 hasBestOaLocation W29642960731 @default.
- W2964296073 hasConcept C127413603 @default.
- W2964296073 hasConcept C154945302 @default.
- W2964296073 hasConcept C201995342 @default.
- W2964296073 hasConcept C204321447 @default.
- W2964296073 hasConcept C2780451532 @default.
- W2964296073 hasConcept C41008148 @default.
- W2964296073 hasConcept C41608201 @default.
- W2964296073 hasConceptScore W2964296073C127413603 @default.
- W2964296073 hasConceptScore W2964296073C154945302 @default.
- W2964296073 hasConceptScore W2964296073C201995342 @default.
- W2964296073 hasConceptScore W2964296073C204321447 @default.
- W2964296073 hasConceptScore W2964296073C2780451532 @default.
- W2964296073 hasConceptScore W2964296073C41008148 @default.
- W2964296073 hasConceptScore W2964296073C41608201 @default.
- W2964296073 hasLocation W29642960731 @default.
- W2964296073 hasLocation W29642960732 @default.
- W2964296073 hasOpenAccess W2964296073 @default.
- W2964296073 hasPrimaryLocation W29642960731 @default.
- W2964296073 hasRelatedWork W1552159754 @default.
- W2964296073 hasRelatedWork W2081647779 @default.
- W2964296073 hasRelatedWork W2148757832 @default.
- W2964296073 hasRelatedWork W2293457016 @default.
- W2964296073 hasRelatedWork W2368651715 @default.
- W2964296073 hasRelatedWork W2611614995 @default.
- W2964296073 hasRelatedWork W2789919619 @default.
- W2964296073 hasRelatedWork W3107474891 @default.
- W2964296073 hasRelatedWork W3185852197 @default.
- W2964296073 hasRelatedWork W4321496520 @default.
- W2964296073 isParatext "false" @default.
- W2964296073 isRetracted "false" @default.
- W2964296073 magId "2964296073" @default.