Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323922104> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4323922104 abstract "Intent recognition is critical for task-oriented dialogue systems. However, for emerging domains and new services, it is difficult to accurately identify the key intent of a conversation due to time-consuming data annotation and comparatively poor model transferability. Therefore, the automatic induction of dialogue intention is very important for intelligent dialogue systems. This paper presents our solution to Track 2 of Intent Induction from Conversations for Task-Oriented Dialogue at the Eleventh Dialogue System Technology Challenge (DSTC11). The essence of intention clustering lies in distinguishing the representation of different dialogue utterances. The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels. Therefore, we propose a multi-stage coarse-to-fine contrastive learning model training scheme including unsupervised contrastive learning pre-training, supervised contrastive learning pre-training, and fine-tuning with joint contrastive learning and clustering to obtain a better dialogue utterance representation model for the clustering task. In the released DSTC11 Track 2 evaluation results, our proposed system ranked first on both of the two subtasks of this Track." @default.
- W4323922104 created "2023-03-12" @default.
- W4323922104 creator A5005572782 @default.
- W4323922104 creator A5017193282 @default.
- W4323922104 creator A5032611421 @default.
- W4323922104 creator A5035801000 @default.
- W4323922104 creator A5052085332 @default.
- W4323922104 creator A5060107207 @default.
- W4323922104 creator A5076447478 @default.
- W4323922104 date "2023-03-08" @default.
- W4323922104 modified "2023-09-26" @default.
- W4323922104 title "Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction" @default.
- W4323922104 doi "https://doi.org/10.48550/arxiv.2303.05034" @default.
- W4323922104 hasPublicationYear "2023" @default.
- W4323922104 type Work @default.
- W4323922104 citedByCount "0" @default.
- W4323922104 crossrefType "posted-content" @default.
- W4323922104 hasAuthorship W4323922104A5005572782 @default.
- W4323922104 hasAuthorship W4323922104A5017193282 @default.
- W4323922104 hasAuthorship W4323922104A5032611421 @default.
- W4323922104 hasAuthorship W4323922104A5035801000 @default.
- W4323922104 hasAuthorship W4323922104A5052085332 @default.
- W4323922104 hasAuthorship W4323922104A5060107207 @default.
- W4323922104 hasAuthorship W4323922104A5076447478 @default.
- W4323922104 hasBestOaLocation W43239221041 @default.
- W4323922104 hasConcept C136764020 @default.
- W4323922104 hasConcept C138885662 @default.
- W4323922104 hasConcept C154945302 @default.
- W4323922104 hasConcept C162324750 @default.
- W4323922104 hasConcept C177264268 @default.
- W4323922104 hasConcept C17744445 @default.
- W4323922104 hasConcept C187736073 @default.
- W4323922104 hasConcept C199360897 @default.
- W4323922104 hasConcept C199539241 @default.
- W4323922104 hasConcept C204321447 @default.
- W4323922104 hasConcept C26517878 @default.
- W4323922104 hasConcept C2775852435 @default.
- W4323922104 hasConcept C2776359362 @default.
- W4323922104 hasConcept C2777200299 @default.
- W4323922104 hasConcept C2777206241 @default.
- W4323922104 hasConcept C2777530160 @default.
- W4323922104 hasConcept C2780451532 @default.
- W4323922104 hasConcept C38652104 @default.
- W4323922104 hasConcept C41008148 @default.
- W4323922104 hasConcept C41895202 @default.
- W4323922104 hasConcept C59404180 @default.
- W4323922104 hasConcept C73555534 @default.
- W4323922104 hasConcept C94625758 @default.
- W4323922104 hasConceptScore W4323922104C136764020 @default.
- W4323922104 hasConceptScore W4323922104C138885662 @default.
- W4323922104 hasConceptScore W4323922104C154945302 @default.
- W4323922104 hasConceptScore W4323922104C162324750 @default.
- W4323922104 hasConceptScore W4323922104C177264268 @default.
- W4323922104 hasConceptScore W4323922104C17744445 @default.
- W4323922104 hasConceptScore W4323922104C187736073 @default.
- W4323922104 hasConceptScore W4323922104C199360897 @default.
- W4323922104 hasConceptScore W4323922104C199539241 @default.
- W4323922104 hasConceptScore W4323922104C204321447 @default.
- W4323922104 hasConceptScore W4323922104C26517878 @default.
- W4323922104 hasConceptScore W4323922104C2775852435 @default.
- W4323922104 hasConceptScore W4323922104C2776359362 @default.
- W4323922104 hasConceptScore W4323922104C2777200299 @default.
- W4323922104 hasConceptScore W4323922104C2777206241 @default.
- W4323922104 hasConceptScore W4323922104C2777530160 @default.
- W4323922104 hasConceptScore W4323922104C2780451532 @default.
- W4323922104 hasConceptScore W4323922104C38652104 @default.
- W4323922104 hasConceptScore W4323922104C41008148 @default.
- W4323922104 hasConceptScore W4323922104C41895202 @default.
- W4323922104 hasConceptScore W4323922104C59404180 @default.
- W4323922104 hasConceptScore W4323922104C73555534 @default.
- W4323922104 hasConceptScore W4323922104C94625758 @default.
- W4323922104 hasLocation W43239221041 @default.
- W4323922104 hasOpenAccess W4323922104 @default.
- W4323922104 hasPrimaryLocation W43239221041 @default.
- W4323922104 hasRelatedWork W1601017932 @default.
- W4323922104 hasRelatedWork W2070147364 @default.
- W4323922104 hasRelatedWork W2093212730 @default.
- W4323922104 hasRelatedWork W2116869842 @default.
- W4323922104 hasRelatedWork W2145634188 @default.
- W4323922104 hasRelatedWork W2171511892 @default.
- W4323922104 hasRelatedWork W2949747155 @default.
- W4323922104 hasRelatedWork W2962898344 @default.
- W4323922104 hasRelatedWork W3107474891 @default.
- W4323922104 hasRelatedWork W4312395240 @default.
- W4323922104 isParatext "false" @default.
- W4323922104 isRetracted "false" @default.
- W4323922104 workType "article" @default.