Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385484930> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4385484930 abstract "A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines. Dialogue disentanglement aims at separating an entangled dialogue into detached sessions, thus increasing the readability of long disordered dialogue. Previous studies mainly focus on message-pair classification and clustering in two-step methods, which cannot guarantee the whole clustering performance in a dialogue. To address this challenge, we propose a simple yet effective model named CluCDD, which aggregates utterances by contrastive learning. More specifically, our model pulls utterances in the same session together and pushes away utterances in different ones. Then a clustering method is adopted to generate predicted clustering labels. Comprehensive experiments conducted on the Movie Dialogue dataset and IRC dataset demonstrate that our model achieves a new state-of-the-art result <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> . <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> Code is available at https://github.com/gaojingsheng/CluCDD" @default.
- W4385484930 created "2023-08-03" @default.
- W4385484930 creator A5026260510 @default.
- W4385484930 creator A5027871520 @default.
- W4385484930 creator A5044897858 @default.
- W4385484930 creator A5063089557 @default.
- W4385484930 creator A5086214932 @default.
- W4385484930 date "2023-06-04" @default.
- W4385484930 modified "2023-09-26" @default.
- W4385484930 title "CluCDD: Contrastive Dialogue Disentanglement Via Clustering" @default.
- W4385484930 cites W2138621090 @default.
- W4385484930 cites W2255466643 @default.
- W4385484930 cites W2561158378 @default.
- W4385484930 cites W2593751037 @default.
- W4385484930 cites W2803119681 @default.
- W4385484930 cites W2949600515 @default.
- W4385484930 cites W2962854379 @default.
- W4385484930 cites W3034545352 @default.
- W4385484930 cites W3101471490 @default.
- W4385484930 cites W3197275000 @default.
- W4385484930 cites W4226047536 @default.
- W4385484930 doi "https://doi.org/10.1109/icasspw59220.2023.10193381" @default.
- W4385484930 hasPublicationYear "2023" @default.
- W4385484930 type Work @default.
- W4385484930 citedByCount "0" @default.
- W4385484930 crossrefType "proceedings-article" @default.
- W4385484930 hasAuthorship W4385484930A5026260510 @default.
- W4385484930 hasAuthorship W4385484930A5027871520 @default.
- W4385484930 hasAuthorship W4385484930A5044897858 @default.
- W4385484930 hasAuthorship W4385484930A5063089557 @default.
- W4385484930 hasAuthorship W4385484930A5086214932 @default.
- W4385484930 hasBestOaLocation W43854849302 @default.
- W4385484930 hasConcept C111472728 @default.
- W4385484930 hasConcept C120665830 @default.
- W4385484930 hasConcept C121332964 @default.
- W4385484930 hasConcept C136764020 @default.
- W4385484930 hasConcept C138885662 @default.
- W4385484930 hasConcept C154504017 @default.
- W4385484930 hasConcept C154945302 @default.
- W4385484930 hasConcept C177264268 @default.
- W4385484930 hasConcept C192209626 @default.
- W4385484930 hasConcept C199360897 @default.
- W4385484930 hasConcept C204321447 @default.
- W4385484930 hasConcept C23123220 @default.
- W4385484930 hasConcept C2776760102 @default.
- W4385484930 hasConcept C2778143727 @default.
- W4385484930 hasConcept C2779182362 @default.
- W4385484930 hasConcept C2780586882 @default.
- W4385484930 hasConcept C41008148 @default.
- W4385484930 hasConcept C73555534 @default.
- W4385484930 hasConceptScore W4385484930C111472728 @default.
- W4385484930 hasConceptScore W4385484930C120665830 @default.
- W4385484930 hasConceptScore W4385484930C121332964 @default.
- W4385484930 hasConceptScore W4385484930C136764020 @default.
- W4385484930 hasConceptScore W4385484930C138885662 @default.
- W4385484930 hasConceptScore W4385484930C154504017 @default.
- W4385484930 hasConceptScore W4385484930C154945302 @default.
- W4385484930 hasConceptScore W4385484930C177264268 @default.
- W4385484930 hasConceptScore W4385484930C192209626 @default.
- W4385484930 hasConceptScore W4385484930C199360897 @default.
- W4385484930 hasConceptScore W4385484930C204321447 @default.
- W4385484930 hasConceptScore W4385484930C23123220 @default.
- W4385484930 hasConceptScore W4385484930C2776760102 @default.
- W4385484930 hasConceptScore W4385484930C2778143727 @default.
- W4385484930 hasConceptScore W4385484930C2779182362 @default.
- W4385484930 hasConceptScore W4385484930C2780586882 @default.
- W4385484930 hasConceptScore W4385484930C41008148 @default.
- W4385484930 hasConceptScore W4385484930C73555534 @default.
- W4385484930 hasFunder F4320321001 @default.
- W4385484930 hasLocation W43854849301 @default.
- W4385484930 hasLocation W43854849302 @default.
- W4385484930 hasOpenAccess W4385484930 @default.
- W4385484930 hasPrimaryLocation W43854849301 @default.
- W4385484930 hasRelatedWork W1882848237 @default.
- W4385484930 hasRelatedWork W2060883057 @default.
- W4385484930 hasRelatedWork W2081830265 @default.
- W4385484930 hasRelatedWork W2348742136 @default.
- W4385484930 hasRelatedWork W2390777183 @default.
- W4385484930 hasRelatedWork W2990199931 @default.
- W4385484930 hasRelatedWork W3086420033 @default.
- W4385484930 hasRelatedWork W3087157779 @default.
- W4385484930 hasRelatedWork W4231927834 @default.
- W4385484930 hasRelatedWork W4306770904 @default.
- W4385484930 isParatext "false" @default.
- W4385484930 isRetracted "false" @default.
- W4385484930 workType "article" @default.