Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198967775> ?p ?o ?g. }
- W3198967775 abstract "Despite the success of neural dialogue systems in achieving high performance on the leader-board, they cannot meet users’ requirements in practice, due to their poor reasoning skills. The underlying reason is that most neural dialogue models only capture the syntactic and semantic information, but fail to model the logical consistency between the dialogue history and the generated response. Recently, a new multi-turn dialogue reasoning task has been proposed, to facilitate dialogue reasoning research. However, this task is challenging, because there are only slight differences between the illogical response and the dialogue history. How to effectively solve this challenge is still worth exploring. This paper proposes a Fine-grained Comparison Model (FCM) to tackle this problem. Inspired by human’s behavior in reading comprehension, a comparison mechanism is proposed to focus on the fine-grained differences in the representation of each response candidate. Specifically, each candidate representation is compared with the whole history to obtain a history consistency representation. Furthermore, the consistency signals between each candidate and the speaker’s own history are considered to drive a model prefer a candidate that is logically consistent with the speaker’s history logic. Finally, the above consistency representations are employed to output a ranking list of the candidate responses for multi-turn dialogue reasoning. Experimental results on two public dialogue datasets show that our method obtains higher ranking scores than the baseline models." @default.
- W3198967775 created "2021-09-27" @default.
- W3198967775 creator A5008043408 @default.
- W3198967775 creator A5020444844 @default.
- W3198967775 creator A5032087333 @default.
- W3198967775 creator A5035164990 @default.
- W3198967775 creator A5041432735 @default.
- W3198967775 creator A5053297393 @default.
- W3198967775 creator A5066907634 @default.
- W3198967775 creator A5077926417 @default.
- W3198967775 date "2021-01-01" @default.
- W3198967775 modified "2023-09-25" @default.
- W3198967775 title "FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning" @default.
- W3198967775 cites W102065888 @default.
- W3198967775 cites W2009593660 @default.
- W3198967775 cites W2581637843 @default.
- W3198967775 cites W2789033601 @default.
- W3198967775 cites W2789078277 @default.
- W3198967775 cites W2798456655 @default.
- W3198967775 cites W2807791032 @default.
- W3198967775 cites W2862781886 @default.
- W3198967775 cites W2891416139 @default.
- W3198967775 cites W2908285010 @default.
- W3198967775 cites W2947812138 @default.
- W3198967775 cites W2952813980 @default.
- W3198967775 cites W2953126480 @default.
- W3198967775 cites W2962854379 @default.
- W3198967775 cites W2962883855 @default.
- W3198967775 cites W2962896208 @default.
- W3198967775 cites W2963341956 @default.
- W3198967775 cites W2963520511 @default.
- W3198967775 cites W2963544536 @default.
- W3198967775 cites W2963986868 @default.
- W3198967775 cites W2964121744 @default.
- W3198967775 cites W2965373594 @default.
- W3198967775 cites W2970648534 @default.
- W3198967775 cites W2972324944 @default.
- W3198967775 cites W3034446185 @default.
- W3198967775 cites W3035356453 @default.
- W3198967775 cites W3094612274 @default.
- W3198967775 cites W3101227179 @default.
- W3198967775 cites W3172448816 @default.
- W3198967775 doi "https://doi.org/10.18653/v1/2021.findings-emnlp.362" @default.
- W3198967775 hasPublicationYear "2021" @default.
- W3198967775 type Work @default.
- W3198967775 sameAs 3198967775 @default.
- W3198967775 citedByCount "0" @default.
- W3198967775 crossrefType "proceedings-article" @default.
- W3198967775 hasAuthorship W3198967775A5008043408 @default.
- W3198967775 hasAuthorship W3198967775A5020444844 @default.
- W3198967775 hasAuthorship W3198967775A5032087333 @default.
- W3198967775 hasAuthorship W3198967775A5035164990 @default.
- W3198967775 hasAuthorship W3198967775A5041432735 @default.
- W3198967775 hasAuthorship W3198967775A5053297393 @default.
- W3198967775 hasAuthorship W3198967775A5066907634 @default.
- W3198967775 hasAuthorship W3198967775A5077926417 @default.
- W3198967775 hasBestOaLocation W31989677751 @default.
- W3198967775 hasConcept C119857082 @default.
- W3198967775 hasConcept C120665830 @default.
- W3198967775 hasConcept C121332964 @default.
- W3198967775 hasConcept C151730666 @default.
- W3198967775 hasConcept C154945302 @default.
- W3198967775 hasConcept C162324750 @default.
- W3198967775 hasConcept C17744445 @default.
- W3198967775 hasConcept C187736073 @default.
- W3198967775 hasConcept C189430467 @default.
- W3198967775 hasConcept C192209626 @default.
- W3198967775 hasConcept C199360897 @default.
- W3198967775 hasConcept C199539241 @default.
- W3198967775 hasConcept C204321447 @default.
- W3198967775 hasConcept C2776359362 @default.
- W3198967775 hasConcept C2776436953 @default.
- W3198967775 hasConcept C2779343474 @default.
- W3198967775 hasConcept C2780451532 @default.
- W3198967775 hasConcept C41008148 @default.
- W3198967775 hasConcept C511192102 @default.
- W3198967775 hasConcept C86803240 @default.
- W3198967775 hasConcept C94625758 @default.
- W3198967775 hasConceptScore W3198967775C119857082 @default.
- W3198967775 hasConceptScore W3198967775C120665830 @default.
- W3198967775 hasConceptScore W3198967775C121332964 @default.
- W3198967775 hasConceptScore W3198967775C151730666 @default.
- W3198967775 hasConceptScore W3198967775C154945302 @default.
- W3198967775 hasConceptScore W3198967775C162324750 @default.
- W3198967775 hasConceptScore W3198967775C17744445 @default.
- W3198967775 hasConceptScore W3198967775C187736073 @default.
- W3198967775 hasConceptScore W3198967775C189430467 @default.
- W3198967775 hasConceptScore W3198967775C192209626 @default.
- W3198967775 hasConceptScore W3198967775C199360897 @default.
- W3198967775 hasConceptScore W3198967775C199539241 @default.
- W3198967775 hasConceptScore W3198967775C204321447 @default.
- W3198967775 hasConceptScore W3198967775C2776359362 @default.
- W3198967775 hasConceptScore W3198967775C2776436953 @default.
- W3198967775 hasConceptScore W3198967775C2779343474 @default.
- W3198967775 hasConceptScore W3198967775C2780451532 @default.
- W3198967775 hasConceptScore W3198967775C41008148 @default.
- W3198967775 hasConceptScore W3198967775C511192102 @default.
- W3198967775 hasConceptScore W3198967775C86803240 @default.
- W3198967775 hasConceptScore W3198967775C94625758 @default.
- W3198967775 hasLocation W31989677751 @default.