“What Do You Mean by That?” A Parser-Independent Interactive Approach for Enhancing Text-to-SQL

• DOI: 10.18653/v1/2020.emnlp-main.561
• Publication Date: 2020-11-29T09:51:46Z
• Authors: Yuntao Li; Bei Chen; Qian Liu; Yan Gao; Jian-Guang Lou; Yan Zhang; Dongmei Zhang
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computation and Language (cs.CL)

In Natural Language Interfaces to Databases systems, the text-to-SQL technique allows users query databases by using natural language questions. Though significant progress in this area has been made recently, most parsers may fall short when they are deployed real systems. One main reason stems from difficulty of fully understanding users' paper, we include human loop and present a novel parser-independent interactive approach (PIIA) that interacts with multi-choice questions can easily work arbitrary parsers. Experiments were conducted on two cross-domain datasets, WikiSQL more complex Spider, five state-of-the-art These demonstrated PIIA is capable enhancing performance limited interaction turns both simulation evaluation.