Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285606144> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4285606144 abstract "Recent research attention for relation extraction has been paid to the dialogue scenario, i.e., dialogue-level relation extraction (DiaRE). Existing DiaRE methods either simply concatenate the utterances in a dialogue into a long piece of text, or employ naive words, sentences or entities to build dialogue graphs, while the structural characteristics in dialogues have not been fully utilized. In this work, we investigate a novel dialogue-level mixed dependency graph (D2G) and an argument reasoning graph (ARG) for DiaRE with a global relation reasoning mechanism. First, we model the entire dialogue into a unified and coherent D2G by explicitly integrating both syntactic and discourse structures, which enables richer semantic and feature learning for relation extraction. Second, we stack an ARG graph on top of D2G to further focus on argument inter-dependency learning and argument representation refinement, for sufficient argument relation inference. In our global reasoning framework, D2G and ARG work collaboratively, iteratively performing lexical, syntactic and semantic information exchange and representation learning over the entire dialogue context. On two DiaRE benchmarks, our framework shows considerable improvements over the current state-of-the-art baselines. Further analyses show that the model effectively solves the long-range dependence issue, and meanwhile gives explainable predictions." @default.
- W4285606144 created "2022-07-16" @default.
- W4285606144 creator A5020441477 @default.
- W4285606144 creator A5035200265 @default.
- W4285606144 creator A5053217291 @default.
- W4285606144 creator A5078354590 @default.
- W4285606144 date "2022-07-01" @default.
- W4285606144 modified "2023-10-14" @default.
- W4285606144 title "Global Inference with Explicit Syntactic and Discourse Structures for Dialogue-Level Relation Extraction" @default.
- W4285606144 doi "https://doi.org/10.24963/ijcai.2022/570" @default.
- W4285606144 hasPublicationYear "2022" @default.
- W4285606144 type Work @default.
- W4285606144 citedByCount "5" @default.
- W4285606144 countsByYear W42856061442023 @default.
- W4285606144 crossrefType "proceedings-article" @default.
- W4285606144 hasAuthorship W4285606144A5020441477 @default.
- W4285606144 hasAuthorship W4285606144A5035200265 @default.
- W4285606144 hasAuthorship W4285606144A5053217291 @default.
- W4285606144 hasAuthorship W4285606144A5078354590 @default.
- W4285606144 hasBestOaLocation W42856061441 @default.
- W4285606144 hasConcept C120665830 @default.
- W4285606144 hasConcept C121332964 @default.
- W4285606144 hasConcept C132525143 @default.
- W4285606144 hasConcept C153604712 @default.
- W4285606144 hasConcept C154945302 @default.
- W4285606144 hasConcept C16311509 @default.
- W4285606144 hasConcept C17744445 @default.
- W4285606144 hasConcept C185592680 @default.
- W4285606144 hasConcept C192209626 @default.
- W4285606144 hasConcept C195807954 @default.
- W4285606144 hasConcept C19768560 @default.
- W4285606144 hasConcept C199539241 @default.
- W4285606144 hasConcept C204321447 @default.
- W4285606144 hasConcept C25343380 @default.
- W4285606144 hasConcept C2776214188 @default.
- W4285606144 hasConcept C2776359362 @default.
- W4285606144 hasConcept C41008148 @default.
- W4285606144 hasConcept C55493867 @default.
- W4285606144 hasConcept C77088390 @default.
- W4285606144 hasConcept C80444323 @default.
- W4285606144 hasConcept C94625758 @default.
- W4285606144 hasConcept C98184364 @default.
- W4285606144 hasConceptScore W4285606144C120665830 @default.
- W4285606144 hasConceptScore W4285606144C121332964 @default.
- W4285606144 hasConceptScore W4285606144C132525143 @default.
- W4285606144 hasConceptScore W4285606144C153604712 @default.
- W4285606144 hasConceptScore W4285606144C154945302 @default.
- W4285606144 hasConceptScore W4285606144C16311509 @default.
- W4285606144 hasConceptScore W4285606144C17744445 @default.
- W4285606144 hasConceptScore W4285606144C185592680 @default.
- W4285606144 hasConceptScore W4285606144C192209626 @default.
- W4285606144 hasConceptScore W4285606144C195807954 @default.
- W4285606144 hasConceptScore W4285606144C19768560 @default.
- W4285606144 hasConceptScore W4285606144C199539241 @default.
- W4285606144 hasConceptScore W4285606144C204321447 @default.
- W4285606144 hasConceptScore W4285606144C25343380 @default.
- W4285606144 hasConceptScore W4285606144C2776214188 @default.
- W4285606144 hasConceptScore W4285606144C2776359362 @default.
- W4285606144 hasConceptScore W4285606144C41008148 @default.
- W4285606144 hasConceptScore W4285606144C55493867 @default.
- W4285606144 hasConceptScore W4285606144C77088390 @default.
- W4285606144 hasConceptScore W4285606144C80444323 @default.
- W4285606144 hasConceptScore W4285606144C94625758 @default.
- W4285606144 hasConceptScore W4285606144C98184364 @default.
- W4285606144 hasLocation W42856061441 @default.
- W4285606144 hasOpenAccess W4285606144 @default.
- W4285606144 hasPrimaryLocation W42856061441 @default.
- W4285606144 hasRelatedWork W2404283144 @default.
- W4285606144 hasRelatedWork W2430210575 @default.
- W4285606144 hasRelatedWork W2903136963 @default.
- W4285606144 hasRelatedWork W2952854166 @default.
- W4285606144 hasRelatedWork W3168129742 @default.
- W4285606144 hasRelatedWork W3203028781 @default.
- W4285606144 hasRelatedWork W3203251273 @default.
- W4285606144 hasRelatedWork W3205801342 @default.
- W4285606144 hasRelatedWork W3207070074 @default.
- W4285606144 hasRelatedWork W4384404817 @default.
- W4285606144 isParatext "false" @default.
- W4285606144 isRetracted "false" @default.
- W4285606144 workType "article" @default.