Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803853046> ?p ?o ?g. }
- W2803853046 abstract "Entity recognition is a widely benchmarked task in natural language processing due to its massive applications. The state-of-the-art solution applies a neural architecture named BiLSTM-CRF to model the language sequences. In this paper, we propose an entity recognition system that improves this neural architecture with two novel techniques. The first technique is Multi-Task Data Selection, which ensures the consistency of data distribution and labeling guidelines between source and target datasets. The other one is constrained decoding using knowledge base. The decoder of the model operates at the document level, and leverages global and external information sources to further improve performance. Extensive experiments have been conducted to show the advantages of each technique. Our system achieves state-of-the-art results on the English entity recognition task in KBP 2017 official evaluation, and it also yields very strong results in other languages." @default.
- W2803853046 created "2018-06-01" @default.
- W2803853046 creator A5046520437 @default.
- W2803853046 creator A5046872618 @default.
- W2803853046 creator A5056002024 @default.
- W2803853046 creator A5090266285 @default.
- W2803853046 date "2018-01-01" @default.
- W2803853046 modified "2023-09-23" @default.
- W2803853046 title "Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding" @default.
- W2803853046 cites W2000411838 @default.
- W2803853046 cites W2047620598 @default.
- W2803853046 cites W2111362445 @default.
- W2803853046 cites W2117278770 @default.
- W2803853046 cites W2144499799 @default.
- W2803853046 cites W2250236394 @default.
- W2803853046 cites W2250539671 @default.
- W2803853046 cites W2251628379 @default.
- W2803853046 cites W2296283641 @default.
- W2803853046 cites W2402144811 @default.
- W2803853046 cites W2508857598 @default.
- W2803853046 cites W2604986524 @default.
- W2803853046 cites W2740006839 @default.
- W2803853046 cites W2805639923 @default.
- W2803853046 cites W2806272805 @default.
- W2803853046 cites W2962902328 @default.
- W2803853046 cites W2963355640 @default.
- W2803853046 cites W2964222246 @default.
- W2803853046 doi "https://doi.org/10.18653/v1/n18-2056" @default.
- W2803853046 hasPublicationYear "2018" @default.
- W2803853046 type Work @default.
- W2803853046 sameAs 2803853046 @default.
- W2803853046 citedByCount "8" @default.
- W2803853046 countsByYear W28038530462018 @default.
- W2803853046 countsByYear W28038530462019 @default.
- W2803853046 countsByYear W28038530462020 @default.
- W2803853046 countsByYear W28038530462021 @default.
- W2803853046 countsByYear W28038530462022 @default.
- W2803853046 crossrefType "proceedings-article" @default.
- W2803853046 hasAuthorship W2803853046A5046520437 @default.
- W2803853046 hasAuthorship W2803853046A5046872618 @default.
- W2803853046 hasAuthorship W2803853046A5056002024 @default.
- W2803853046 hasAuthorship W2803853046A5090266285 @default.
- W2803853046 hasBestOaLocation W28038530461 @default.
- W2803853046 hasConcept C11413529 @default.
- W2803853046 hasConcept C123657996 @default.
- W2803853046 hasConcept C137293760 @default.
- W2803853046 hasConcept C142362112 @default.
- W2803853046 hasConcept C153349607 @default.
- W2803853046 hasConcept C154945302 @default.
- W2803853046 hasConcept C162324750 @default.
- W2803853046 hasConcept C187736073 @default.
- W2803853046 hasConcept C195324797 @default.
- W2803853046 hasConcept C199360897 @default.
- W2803853046 hasConcept C204321447 @default.
- W2803853046 hasConcept C2776436953 @default.
- W2803853046 hasConcept C2779135771 @default.
- W2803853046 hasConcept C2780451532 @default.
- W2803853046 hasConcept C41008148 @default.
- W2803853046 hasConcept C4554734 @default.
- W2803853046 hasConcept C48103436 @default.
- W2803853046 hasConcept C50644808 @default.
- W2803853046 hasConcept C57273362 @default.
- W2803853046 hasConcept C81917197 @default.
- W2803853046 hasConceptScore W2803853046C11413529 @default.
- W2803853046 hasConceptScore W2803853046C123657996 @default.
- W2803853046 hasConceptScore W2803853046C137293760 @default.
- W2803853046 hasConceptScore W2803853046C142362112 @default.
- W2803853046 hasConceptScore W2803853046C153349607 @default.
- W2803853046 hasConceptScore W2803853046C154945302 @default.
- W2803853046 hasConceptScore W2803853046C162324750 @default.
- W2803853046 hasConceptScore W2803853046C187736073 @default.
- W2803853046 hasConceptScore W2803853046C195324797 @default.
- W2803853046 hasConceptScore W2803853046C199360897 @default.
- W2803853046 hasConceptScore W2803853046C204321447 @default.
- W2803853046 hasConceptScore W2803853046C2776436953 @default.
- W2803853046 hasConceptScore W2803853046C2779135771 @default.
- W2803853046 hasConceptScore W2803853046C2780451532 @default.
- W2803853046 hasConceptScore W2803853046C41008148 @default.
- W2803853046 hasConceptScore W2803853046C4554734 @default.
- W2803853046 hasConceptScore W2803853046C48103436 @default.
- W2803853046 hasConceptScore W2803853046C50644808 @default.
- W2803853046 hasConceptScore W2803853046C57273362 @default.
- W2803853046 hasConceptScore W2803853046C81917197 @default.
- W2803853046 hasLocation W28038530461 @default.
- W2803853046 hasOpenAccess W2803853046 @default.
- W2803853046 hasPrimaryLocation W28038530461 @default.
- W2803853046 hasRelatedWork W2017615984 @default.
- W2803853046 hasRelatedWork W2234895705 @default.
- W2803853046 hasRelatedWork W2296283641 @default.
- W2803853046 hasRelatedWork W2798460144 @default.
- W2803853046 hasRelatedWork W2913075819 @default.
- W2803853046 hasRelatedWork W2918598763 @default.
- W2803853046 hasRelatedWork W2948614377 @default.
- W2803853046 hasRelatedWork W2952844669 @default.
- W2803853046 hasRelatedWork W2956423934 @default.
- W2803853046 hasRelatedWork W2963103814 @default.
- W2803853046 hasRelatedWork W2963561757 @default.
- W2803853046 hasRelatedWork W2963628345 @default.
- W2803853046 hasRelatedWork W2988193569 @default.
- W2803853046 hasRelatedWork W3004177491 @default.