Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead

Sree Hari Krishnan Parthasarathi, Lu Zeng, Dilek Hakkani-Tur

Research output: Contribution to journalConference articlepeer-review

Abstract

Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family, in conjunction with constrained decoding. With multi-tasking (MT) over coherent tasks with discrete prompts during training, we improve over specialized text-to-SQL T5-family models. Based on Oracle analyses over n-best hypotheses, we apply a query plan model and a schema linking algorithm as rerankers. Combining MT and reranking, our results using T53B show absolute accuracy improvements of 1.0% in exact match and 3.4% in execution match over a SOTA baseline on CoSQL. While these gains consistently manifest at turn level, context dependent turns are considerably harder. We conduct studies to tease apart errors attributable to domain and compositional generalization, with the latter remaining a challenge for multi-turn conversations, especially in generating SQL with unseen parse trees.

Keywords

  • Conversational Text-To-SQL

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead'. Together they form a unique fingerprint.

Cite this