Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQL

TL;DR

This paper introduces a context modeling strategy that explicitly captures semantic changes in multi-turn conversational queries, significantly improving text-to-SQL conversion accuracy.

Contribution

It proposes two auxiliary conversational modeling tasks at turn and conversation levels to enhance multi-turn semantic parsing performance.

Findings

Achieved new state-of-the-art results on a large-scale conversational text-to-SQL dataset.

Explicit semantic change modeling improves multi-turn query understanding.

Auxiliary tasks effectively boost semantic parsing accuracy.

Abstract

Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations. One of the most intractable problems of conversational text-to-SQL is modelling the semantics of multi-turn queries and gathering the proper information required for the current query. This paper shows that explicitly modelling the semantic changes by adding each turn and the summarization of the whole context can bring better performance on converting conversational queries into SQLs. In particular, we propose two conversational modelling tasks in both turn grain and conversation grain. These two tasks simply work as auxiliary training tasks to help with multi-turn conversational semantic parsing. We conducted empirical studies and achieved new state-of-the-art results on the large-scale open-domain conversational text-to-SQL dataset. The results demonstrate that the proposed mechanism significantly improves the performance of multi-turn semantic parsing.