Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102602010> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3102602010 abstract "Detecting negation and speculation in language has been a task of considerable interest to the biomedical community, as it is a key component of Information Extraction systems from Biomedical documents. Prior work has individually addressed Negation Detection and Speculation Detection, and both have been addressed in the same way, using 2 stage pipelined approach: Cue Detection followed by Scope Resolution. In this paper, we propose Multitask learning approaches over 2 sets of tasks: Negation Cue Detection & Speculation Cue Detection, and Negation Scope Resolution & Speculation Scope Resolution. We utilise transformer-based architectures like BERT, XLNet and RoBERTa as our core model architecture, and finetune these using the Multitask learning approaches. We show that this Multitask Learning approach outperforms the single task learning approach, and report new state-of-the-art results on Negation and Speculation Scope Resolution on the BioScope Corpus and the SFU Review Corpus." @default.
- W3102602010 created "2020-11-23" @default.
- W3102602010 creator A5044322804 @default.
- W3102602010 creator A5052764514 @default.
- W3102602010 date "2020-01-01" @default.
- W3102602010 modified "2023-10-15" @default.
- W3102602010 title "Multitask Learning of Negation and Speculation using Transformers" @default.
- W3102602010 cites W133539977 @default.
- W3102602010 cites W1588558467 @default.
- W3102602010 cites W1910766207 @default.
- W3102602010 cites W1961993270 @default.
- W3102602010 cites W2032021697 @default.
- W3102602010 cites W2043335066 @default.
- W3102602010 cites W2086817924 @default.
- W3102602010 cites W2149147504 @default.
- W3102602010 cites W2159230276 @default.
- W3102602010 cites W2169028566 @default.
- W3102602010 cites W2171660026 @default.
- W3102602010 cites W2566847560 @default.
- W3102602010 cites W2905530341 @default.
- W3102602010 cites W2963341956 @default.
- W3102602010 cites W2965373594 @default.
- W3102602010 cites W2970597249 @default.
- W3102602010 cites W2975195127 @default.
- W3102602010 cites W3000132966 @default.
- W3102602010 cites W3031105340 @default.
- W3102602010 cites W3103291281 @default.
- W3102602010 doi "https://doi.org/10.18653/v1/2020.louhi-1.9" @default.
- W3102602010 hasPublicationYear "2020" @default.
- W3102602010 type Work @default.
- W3102602010 sameAs 3102602010 @default.
- W3102602010 citedByCount "12" @default.
- W3102602010 countsByYear W31026020102021 @default.
- W3102602010 countsByYear W31026020102022 @default.
- W3102602010 countsByYear W31026020102023 @default.
- W3102602010 crossrefType "proceedings-article" @default.
- W3102602010 hasAuthorship W3102602010A5044322804 @default.
- W3102602010 hasAuthorship W3102602010A5052764514 @default.
- W3102602010 hasBestOaLocation W31026020101 @default.
- W3102602010 hasConcept C119599485 @default.
- W3102602010 hasConcept C119857082 @default.
- W3102602010 hasConcept C127413603 @default.
- W3102602010 hasConcept C139719470 @default.
- W3102602010 hasConcept C154945302 @default.
- W3102602010 hasConcept C162324750 @default.
- W3102602010 hasConcept C165801399 @default.
- W3102602010 hasConcept C199360897 @default.
- W3102602010 hasConcept C201995342 @default.
- W3102602010 hasConcept C204321447 @default.
- W3102602010 hasConcept C2185349 @default.
- W3102602010 hasConcept C2778012447 @default.
- W3102602010 hasConcept C2780451532 @default.
- W3102602010 hasConcept C28006648 @default.
- W3102602010 hasConcept C41008148 @default.
- W3102602010 hasConcept C47941915 @default.
- W3102602010 hasConcept C66322947 @default.
- W3102602010 hasConceptScore W3102602010C119599485 @default.
- W3102602010 hasConceptScore W3102602010C119857082 @default.
- W3102602010 hasConceptScore W3102602010C127413603 @default.
- W3102602010 hasConceptScore W3102602010C139719470 @default.
- W3102602010 hasConceptScore W3102602010C154945302 @default.
- W3102602010 hasConceptScore W3102602010C162324750 @default.
- W3102602010 hasConceptScore W3102602010C165801399 @default.
- W3102602010 hasConceptScore W3102602010C199360897 @default.
- W3102602010 hasConceptScore W3102602010C201995342 @default.
- W3102602010 hasConceptScore W3102602010C204321447 @default.
- W3102602010 hasConceptScore W3102602010C2185349 @default.
- W3102602010 hasConceptScore W3102602010C2778012447 @default.
- W3102602010 hasConceptScore W3102602010C2780451532 @default.
- W3102602010 hasConceptScore W3102602010C28006648 @default.
- W3102602010 hasConceptScore W3102602010C41008148 @default.
- W3102602010 hasConceptScore W3102602010C47941915 @default.
- W3102602010 hasConceptScore W3102602010C66322947 @default.
- W3102602010 hasLocation W31026020101 @default.
- W3102602010 hasOpenAccess W3102602010 @default.
- W3102602010 hasPrimaryLocation W31026020101 @default.
- W3102602010 hasRelatedWork W2076161440 @default.
- W3102602010 hasRelatedWork W2147782221 @default.
- W3102602010 hasRelatedWork W2489870153 @default.
- W3102602010 hasRelatedWork W2799624154 @default.
- W3102602010 hasRelatedWork W2980823240 @default.
- W3102602010 hasRelatedWork W3091416521 @default.
- W3102602010 hasRelatedWork W3107943460 @default.
- W3102602010 hasRelatedWork W4243792164 @default.
- W3102602010 hasRelatedWork W4250172181 @default.
- W3102602010 hasRelatedWork W76425264 @default.
- W3102602010 isParatext "false" @default.
- W3102602010 isRetracted "false" @default.
- W3102602010 magId "3102602010" @default.
- W3102602010 workType "article" @default.