Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206080127> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3206080127 abstract "Constituency parsing and nested named entity recognition (NER) are similar tasks since they both aim to predict a collection of nested and non-crossing spans. In this work, we cast nested NER to constituency parsing and propose a novel pointing mechanism for bottom-up parsing to tackle both tasks. The key idea is based on the observation that if we traverse a constituency tree in post-order, i.e., visiting a parent after its children, then two consecutively visited spans would share a boundary. Our model tracks the shared boundaries and predicts the next boundary at each step by leveraging a pointer network. As a result, it needs only linear steps to parse and thus is efficient. It also maintains a parsing configuration for structural consistency, i.e., always outputting valid trees. Experimentally, our model achieves the state-of-the-art performance on PTB among all BERT-based models (96.01 F1 score) and competitive performance on CTB7 in constituency parsing; and it also achieves strong performance on three benchmark datasets of nested NER: ACE2004, ACE2005, and GENIA. Our code will be available at https://github.com/xxxxx." @default.
- W3206080127 created "2021-10-25" @default.
- W3206080127 creator A5040350578 @default.
- W3206080127 creator A5072165642 @default.
- W3206080127 date "2022-01-01" @default.
- W3206080127 modified "2023-10-14" @default.
- W3206080127 title "Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks" @default.
- W3206080127 cites W2047477415 @default.
- W3206080127 cites W2064675550 @default.
- W3206080127 cites W2096204319 @default.
- W3206080127 cites W2250710764 @default.
- W3206080127 cites W2563495010 @default.
- W3206080127 cites W2799211465 @default.
- W3206080127 cites W2891570996 @default.
- W3206080127 cites W2963069010 @default.
- W3206080127 cites W2963073938 @default.
- W3206080127 cites W2963084773 @default.
- W3206080127 cites W2963341956 @default.
- W3206080127 cites W2963372751 @default.
- W3206080127 cites W2963643701 @default.
- W3206080127 cites W2963971322 @default.
- W3206080127 cites W2964030814 @default.
- W3206080127 cites W2964096343 @default.
- W3206080127 cites W2964121744 @default.
- W3206080127 cites W2996824315 @default.
- W3206080127 cites W3034744126 @default.
- W3206080127 cites W3035246734 @default.
- W3206080127 cites W3035543689 @default.
- W3206080127 cites W3090015871 @default.
- W3206080127 cites W3101638898 @default.
- W3206080127 cites W3102085674 @default.
- W3206080127 cites W3104588838 @default.
- W3206080127 cites W3160948941 @default.
- W3206080127 cites W3163944651 @default.
- W3206080127 cites W3173293897 @default.
- W3206080127 cites W3176680950 @default.
- W3206080127 cites W3176971429 @default.
- W3206080127 cites W3177329835 @default.
- W3206080127 cites W3024604895 @default.
- W3206080127 doi "https://doi.org/10.18653/v1/2022.acl-long.171" @default.
- W3206080127 hasPublicationYear "2022" @default.
- W3206080127 type Work @default.
- W3206080127 sameAs 3206080127 @default.
- W3206080127 citedByCount "4" @default.
- W3206080127 countsByYear W32060801272023 @default.
- W3206080127 crossrefType "proceedings-article" @default.
- W3206080127 hasAuthorship W3206080127A5040350578 @default.
- W3206080127 hasAuthorship W3206080127A5072165642 @default.
- W3206080127 hasBestOaLocation W32060801271 @default.
- W3206080127 hasConcept C13280743 @default.
- W3206080127 hasConcept C150202949 @default.
- W3206080127 hasConcept C154945302 @default.
- W3206080127 hasConcept C162324750 @default.
- W3206080127 hasConcept C176809094 @default.
- W3206080127 hasConcept C185798385 @default.
- W3206080127 hasConcept C186644900 @default.
- W3206080127 hasConcept C187736073 @default.
- W3206080127 hasConcept C199360897 @default.
- W3206080127 hasConcept C204321447 @default.
- W3206080127 hasConcept C205649164 @default.
- W3206080127 hasConcept C2779135771 @default.
- W3206080127 hasConcept C2780451532 @default.
- W3206080127 hasConcept C41008148 @default.
- W3206080127 hasConceptScore W3206080127C13280743 @default.
- W3206080127 hasConceptScore W3206080127C150202949 @default.
- W3206080127 hasConceptScore W3206080127C154945302 @default.
- W3206080127 hasConceptScore W3206080127C162324750 @default.
- W3206080127 hasConceptScore W3206080127C176809094 @default.
- W3206080127 hasConceptScore W3206080127C185798385 @default.
- W3206080127 hasConceptScore W3206080127C186644900 @default.
- W3206080127 hasConceptScore W3206080127C187736073 @default.
- W3206080127 hasConceptScore W3206080127C199360897 @default.
- W3206080127 hasConceptScore W3206080127C204321447 @default.
- W3206080127 hasConceptScore W3206080127C205649164 @default.
- W3206080127 hasConceptScore W3206080127C2779135771 @default.
- W3206080127 hasConceptScore W3206080127C2780451532 @default.
- W3206080127 hasConceptScore W3206080127C41008148 @default.
- W3206080127 hasLocation W32060801271 @default.
- W3206080127 hasLocation W32060801272 @default.
- W3206080127 hasOpenAccess W3206080127 @default.
- W3206080127 hasPrimaryLocation W32060801271 @default.
- W3206080127 hasRelatedWork W1998962249 @default.
- W3206080127 hasRelatedWork W2026046761 @default.
- W3206080127 hasRelatedWork W2070147537 @default.
- W3206080127 hasRelatedWork W2167662847 @default.
- W3206080127 hasRelatedWork W2502722637 @default.
- W3206080127 hasRelatedWork W3122237579 @default.
- W3206080127 hasRelatedWork W4235735989 @default.
- W3206080127 hasRelatedWork W1551406738 @default.
- W3206080127 hasRelatedWork W2467097043 @default.
- W3206080127 hasRelatedWork W2474495446 @default.
- W3206080127 isParatext "false" @default.
- W3206080127 isRetracted "false" @default.
- W3206080127 magId "3206080127" @default.
- W3206080127 workType "article" @default.