T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing
Abstract: Translating natural language queries into SQLs in a seq2seq manner has attracted much attention recently. However, compared with abstract-syntactic-tree-based SQL generation, seq2seq semantic parsers face much more challenges, including poor quality on schematical information prediction and poor semantic coherence between natural language queries and SQLs. This paper analyses the above difficulties and proposes a seq2seq-oriented decoding strategy called SR, which includes a new intermediate representation SSQL and a reranking method with score re-estimator to solve the above obstacles respectively. Experimental results demonstrate the effectiveness of our proposed techniques and T5-SR-3b achieves new state-of-the-art results on the Spider dataset.
- Li Dong and Mirella Lapata, “Language to logical form with neural attention,” in Proc. of ACL, 2016.
- “Unifiedskg: Unifying and multi-tasking structured knowledge grounding with text-to-text language models,” CoRR, 2022.
- “SyntaxSQLNet: Syntax tree networks for complex and cross-domain text-to-SQL task,” in Proc. of EMNLP, 2018.
- “RAT-SQL: Relation-aware schema encoding and linking for text-to-SQL parsers,” in Proc. of ACL, 2020.
- “PICARD: Parsing incrementally for constrained auto-regressive decoding from language models,” in Proc. of EMNLP, 2021.
- “Exploring the limits of transfer learning with a unified text-to-text transformer,” Journal of Machine Learning Research, 2020.
- “Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task,” in Proc. of EMNLP, 2018.
- “Towards complex text-to-SQL in cross-domain database with intermediate representation,” in Proc. of ACL, 2019.
- “IGSQL: Database schema interaction graph based neural model for context-dependent text-to-SQL generation,” in Proc. of EMNLP, 2020.
- “ShadowGNN: Graph projection neural network for text-to-SQL parser,” in Proc. of NAACL, 2021.
- “LGESQL: Line graph enhanced text-to-SQL model with mixed local and non-local relations,” in Proc. of ACL, 2021.
- “HIE-SQL: History information enhanced network for context-dependent text-to-SQL semantic parsing,” in Proc. of ACL Findings, 2022.
- “Structure-grounded pretraining for text-to-SQL,” in Proc. of NAACL, 2021.
- “Unisar: A unified structure-aware autoregressive language model for text-to-sql,” CoRR, 2022.
- “Pointer networks,” Proc. of NeurIPS, 2015.
- “Incorporating copying mechanism in sequence-to-sequence learning,” in Proc. of ACL, 2016.
- “Bridging textual and tabular data for cross-domain text-to-SQL semantic parsing,” in Proc. of EMNLP Findings, 2020.
- “Natural SQL: Making SQL easier to infer from natural language specifications,” in Proc. of EMNLP Findings, 2021.
- “Reranking for neural semantic parsing,” in Proc. of ACL, 2019.
- “Towards robustness of text-to-SQL models against synonym substitution,” in Proc. of ACL, 2021.
- “Learning contextual representations for semantic parsing with generation-augmented pre-training,” in Proc. of AAAI, 2021.
- “SmBoP: Semi-autoregressive bottom-up semantic parsing,” in Proc. of NAACL, 2021.
- “S22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTSQL: Injecting syntax to question-schema interaction graph encoder for text-to-SQL parsers,” in Proc. of ACL Findings, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.