T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing

Yuntao Li, Zhenpeng Su, Yutian Li, Hanchu Zhang, Sirui Wang +2 more
6/14/2023
cs.CLcs.AI

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL

84% match1 repo2812023

Prompt-based Learning for Text Readability Assessment

78% match1 repo42023

Decoupling SQL Query Hardness Parsing for Text-to-SQL

78% match1 repo22023

Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models

77% match1 repo292023

Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding

77% match1 repo32023

UNITE: A Unified Benchmark for Text-to-SQL Evaluation

76% match1 repo882023

Cite this paper

@article{li2023tsr,
  title  = {T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing},
  author = {Yuntao Li and Zhenpeng Su and Yutian Li and Hanchu Zhang and Sirui Wang and Wei Wu and Yan Zhang},
  year   = {2023},
  eprint = {2306.08368},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.08368v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.08368.svg)](https://codeofpaper.com/paper/2306.08368)

Discussion