Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174921180> ?p ?o ?g. }
- W3174921180 abstract "Recently, Text-to-SQL for multi-turn dialogue has attracted great interest. Here, the user input of the current turn is parsed into the corresponding SQL query of the appropriate database, given all previous dialogue history. Current approaches mostly employ end-to-end models and consequently face two challenges. First, dialogue history modeling and Text-to-SQL parsing are implicitly combined, hence it is hard to carry out interpretable analysis and obtain targeted improvement. Second, SQL annotation of multi-turn dialogue is very expensive, leading to training data sparsity. In this paper, we propose a novel decoupled multi-turn Text-to-SQL framework, where an utterance rewrite model first explicitly solves completion of dialogue context, and then a single-turn Text-to-SQL parser follows. A dual learning approach is also proposed for the utterance rewrite model to address the data sparsity problem. Compared with end-to-end approaches, the proposed decoupled method can achieve excellent performance without any annotated in-domain data. With just a few annotated rewrite cases, the decoupled method outperforms the released state-of-the-art end-to-end models on both SParC and CoSQL datasets." @default.
- W3174921180 created "2021-07-05" @default.
- W3174921180 creator A5020434567 @default.
- W3174921180 creator A5033252354 @default.
- W3174921180 creator A5033988662 @default.
- W3174921180 creator A5043098653 @default.
- W3174921180 creator A5071074966 @default.
- W3174921180 creator A5081865665 @default.
- W3174921180 creator A5087018671 @default.
- W3174921180 date "2021-01-01" @default.
- W3174921180 modified "2023-10-14" @default.
- W3174921180 title "Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL" @default.
- W3174921180 cites W1901129140 @default.
- W3174921180 cites W2047237057 @default.
- W3174921180 cites W2048679005 @default.
- W3174921180 cites W2145618437 @default.
- W3174921180 cites W2155027007 @default.
- W3174921180 cites W2546938941 @default.
- W3174921180 cites W2606974598 @default.
- W3174921180 cites W2624022918 @default.
- W3174921180 cites W2751448157 @default.
- W3174921180 cites W2803595284 @default.
- W3174921180 cites W2891955644 @default.
- W3174921180 cites W2921671634 @default.
- W3174921180 cites W2963106169 @default.
- W3174921180 cites W2963206679 @default.
- W3174921180 cites W2963403868 @default.
- W3174921180 cites W2970110247 @default.
- W3174921180 cites W2970971581 @default.
- W3174921180 cites W2970996870 @default.
- W3174921180 cites W2971377618 @default.
- W3174921180 cites W2972571786 @default.
- W3174921180 cites W2998228050 @default.
- W3174921180 cites W2998235597 @default.
- W3174921180 cites W3015974317 @default.
- W3174921180 cites W3034196295 @default.
- W3174921180 cites W3034475786 @default.
- W3174921180 cites W3034835156 @default.
- W3174921180 cites W3035169992 @default.
- W3174921180 cites W3088415854 @default.
- W3174921180 cites W3088505551 @default.
- W3174921180 cites W3091229675 @default.
- W3174921180 cites W3098824823 @default.
- W3174921180 cites W3100063812 @default.
- W3174921180 cites W3103291908 @default.
- W3174921180 cites W3104395172 @default.
- W3174921180 cites W3116083993 @default.
- W3174921180 cites W3120409403 @default.
- W3174921180 cites W3170656151 @default.
- W3174921180 cites W3170698273 @default.
- W3174921180 doi "https://doi.org/10.18653/v1/2021.findings-acl.270" @default.
- W3174921180 hasPublicationYear "2021" @default.
- W3174921180 type Work @default.
- W3174921180 sameAs 3174921180 @default.
- W3174921180 citedByCount "3" @default.
- W3174921180 countsByYear W31749211802022 @default.
- W3174921180 countsByYear W31749211802023 @default.
- W3174921180 crossrefType "proceedings-article" @default.
- W3174921180 hasAuthorship W3174921180A5020434567 @default.
- W3174921180 hasAuthorship W3174921180A5033252354 @default.
- W3174921180 hasAuthorship W3174921180A5033988662 @default.
- W3174921180 hasAuthorship W3174921180A5043098653 @default.
- W3174921180 hasAuthorship W3174921180A5071074966 @default.
- W3174921180 hasAuthorship W3174921180A5081865665 @default.
- W3174921180 hasAuthorship W3174921180A5087018671 @default.
- W3174921180 hasBestOaLocation W31749211801 @default.
- W3174921180 hasConcept C154945302 @default.
- W3174921180 hasConcept C185592680 @default.
- W3174921180 hasConcept C186644900 @default.
- W3174921180 hasConcept C199360897 @default.
- W3174921180 hasConcept C204321447 @default.
- W3174921180 hasConcept C41008148 @default.
- W3174921180 hasConcept C510870499 @default.
- W3174921180 hasConcept C55493867 @default.
- W3174921180 hasConcept C85641259 @default.
- W3174921180 hasConceptScore W3174921180C154945302 @default.
- W3174921180 hasConceptScore W3174921180C185592680 @default.
- W3174921180 hasConceptScore W3174921180C186644900 @default.
- W3174921180 hasConceptScore W3174921180C199360897 @default.
- W3174921180 hasConceptScore W3174921180C204321447 @default.
- W3174921180 hasConceptScore W3174921180C41008148 @default.
- W3174921180 hasConceptScore W3174921180C510870499 @default.
- W3174921180 hasConceptScore W3174921180C55493867 @default.
- W3174921180 hasConceptScore W3174921180C85641259 @default.
- W3174921180 hasLocation W31749211801 @default.
- W3174921180 hasLocation W31749211802 @default.
- W3174921180 hasOpenAccess W3174921180 @default.
- W3174921180 hasPrimaryLocation W31749211801 @default.
- W3174921180 hasRelatedWork W1552159754 @default.
- W3174921180 hasRelatedWork W1806995473 @default.
- W3174921180 hasRelatedWork W2026046761 @default.
- W3174921180 hasRelatedWork W2070147537 @default.
- W3174921180 hasRelatedWork W2167662847 @default.
- W3174921180 hasRelatedWork W2382501300 @default.
- W3174921180 hasRelatedWork W2502722637 @default.
- W3174921180 hasRelatedWork W3107474891 @default.
- W3174921180 hasRelatedWork W4235735989 @default.
- W3174921180 hasRelatedWork W2467097043 @default.
- W3174921180 isParatext "false" @default.
- W3174921180 isRetracted "false" @default.