Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312193374> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4312193374 endingPage "1065" @default.
- W4312193374 startingPage "1043" @default.
- W4312193374 abstract "Abstract Understanding various historical entity information (e.g., persons, locations, and time) plays a very important role in reasoning about the developments of historical events. With the increasing concern about the fields of digital humanities and natural language processing, named entity recognition (NER) provides a feasible solution for automatically extracting these entities from historical texts, especially in Chinese historical research. However, previous approaches are domain-specific, ineffective with relatively low accuracy, and non-interpretable, which hinders the development of NER in Chinese history. In this paper, we propose a new hybrid deep learning model called “subword-based ensemble network” (SEN), by incorporating subword information and a novel attention fusion mechanism. The experiments on a massive self-built Chinese historical corpus CMAG show that SEN has achieved the best with 93.87% for F1-micro and 89.70% for F1-macro, compared with other advanced models. Further investigation reveals that SEN has a strong generalization ability of NER on Chinese historical texts, which is not only relatively insensitive to the categories with fewer annotation labels (e.g., OFI) but can also accurately capture diverse local and global semantic relations. Our research demonstrates the effectiveness of the integration of subword information and attention fusion, which provides an inspiring solution for the practical use of entity extraction in the Chinese historical domain." @default.
- W4312193374 created "2023-01-04" @default.
- W4312193374 creator A5020347590 @default.
- W4312193374 creator A5049482136 @default.
- W4312193374 creator A5081504976 @default.
- W4312193374 date "2022-12-22" @default.
- W4312193374 modified "2023-10-11" @default.
- W4312193374 title "SEN: A subword-based ensemble network for Chinese historical entity extraction" @default.
- W4312193374 cites W1594229598 @default.
- W4312193374 cites W1989517911 @default.
- W4312193374 cites W2016601637 @default.
- W4312193374 cites W2064675550 @default.
- W4312193374 cites W2123167375 @default.
- W4312193374 cites W2142384583 @default.
- W4312193374 cites W2144502291 @default.
- W4312193374 cites W2200207311 @default.
- W4312193374 cites W2250539671 @default.
- W4312193374 cites W2553582420 @default.
- W4312193374 cites W2604295344 @default.
- W4312193374 cites W2767546521 @default.
- W4312193374 cites W2788009253 @default.
- W4312193374 cites W2886923263 @default.
- W4312193374 cites W2894851285 @default.
- W4312193374 cites W2946308046 @default.
- W4312193374 cites W2950953300 @default.
- W4312193374 cites W2962902328 @default.
- W4312193374 cites W2963625095 @default.
- W4312193374 cites W2964144280 @default.
- W4312193374 cites W2965690110 @default.
- W4312193374 cites W2974511542 @default.
- W4312193374 cites W2986753851 @default.
- W4312193374 cites W2997900951 @default.
- W4312193374 cites W3011594683 @default.
- W4312193374 cites W3048497270 @default.
- W4312193374 cites W3088019499 @default.
- W4312193374 cites W3089319073 @default.
- W4312193374 cites W3103921574 @default.
- W4312193374 cites W3136686455 @default.
- W4312193374 cites W3151019514 @default.
- W4312193374 cites W3174142642 @default.
- W4312193374 cites W3210190743 @default.
- W4312193374 cites W4245736198 @default.
- W4312193374 doi "https://doi.org/10.1017/s1351324922000493" @default.
- W4312193374 hasPublicationYear "2022" @default.
- W4312193374 type Work @default.
- W4312193374 citedByCount "0" @default.
- W4312193374 crossrefType "journal-article" @default.
- W4312193374 hasAuthorship W4312193374A5020347590 @default.
- W4312193374 hasAuthorship W4312193374A5049482136 @default.
- W4312193374 hasAuthorship W4312193374A5081504976 @default.
- W4312193374 hasConcept C134306372 @default.
- W4312193374 hasConcept C154945302 @default.
- W4312193374 hasConcept C162324750 @default.
- W4312193374 hasConcept C187736073 @default.
- W4312193374 hasConcept C195807954 @default.
- W4312193374 hasConcept C204321447 @default.
- W4312193374 hasConcept C2776321320 @default.
- W4312193374 hasConcept C2779135771 @default.
- W4312193374 hasConcept C2780451532 @default.
- W4312193374 hasConcept C33923547 @default.
- W4312193374 hasConcept C36503486 @default.
- W4312193374 hasConcept C41008148 @default.
- W4312193374 hasConceptScore W4312193374C134306372 @default.
- W4312193374 hasConceptScore W4312193374C154945302 @default.
- W4312193374 hasConceptScore W4312193374C162324750 @default.
- W4312193374 hasConceptScore W4312193374C187736073 @default.
- W4312193374 hasConceptScore W4312193374C195807954 @default.
- W4312193374 hasConceptScore W4312193374C204321447 @default.
- W4312193374 hasConceptScore W4312193374C2776321320 @default.
- W4312193374 hasConceptScore W4312193374C2779135771 @default.
- W4312193374 hasConceptScore W4312193374C2780451532 @default.
- W4312193374 hasConceptScore W4312193374C33923547 @default.
- W4312193374 hasConceptScore W4312193374C36503486 @default.
- W4312193374 hasConceptScore W4312193374C41008148 @default.
- W4312193374 hasIssue "4" @default.
- W4312193374 hasLocation W43121933741 @default.
- W4312193374 hasOpenAccess W4312193374 @default.
- W4312193374 hasPrimaryLocation W43121933741 @default.
- W4312193374 hasRelatedWork W1605730749 @default.
- W4312193374 hasRelatedWork W2287770975 @default.
- W4312193374 hasRelatedWork W2886890203 @default.
- W4312193374 hasRelatedWork W2916255597 @default.
- W4312193374 hasRelatedWork W2983934248 @default.
- W4312193374 hasRelatedWork W3017222382 @default.
- W4312193374 hasRelatedWork W3128216712 @default.
- W4312193374 hasRelatedWork W3136915866 @default.
- W4312193374 hasRelatedWork W4313535650 @default.
- W4312193374 hasRelatedWork W4377865234 @default.
- W4312193374 hasVolume "29" @default.
- W4312193374 isParatext "false" @default.
- W4312193374 isRetracted "false" @default.
- W4312193374 workType "article" @default.