English

A Split-and-Recombine Approach for Follow-up Query Analysis

Computation and Language 2019-09-20 v1 Artificial Intelligence

Abstract

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent natural language queries with contextual information. To accomplish the task, we propose STAR, a novel approach with a well-designed two-phase process. It is parser-independent and able to handle multifarious follow-up scenarios in different domains. Experiments on the FollowUp dataset show that STAR outperforms the state-of-the-art baseline by a large margin of nearly 8%. The superiority on parsing results verifies the feasibility of follow-up query analysis. We also explore the extensibility of STAR on the SQA dataset, which is very promising.

Keywords

Cite

@article{arxiv.1909.08905,
  title  = {A Split-and-Recombine Approach for Follow-up Query Analysis},
  author = {Qian Liu and Bei Chen and Haoyan Liu and Lei Fang and Jian-Guang Lou and Bin Zhou and Dongmei Zhang},
  journal= {arXiv preprint arXiv:1909.08905},
  year   = {2019}
}

Comments

Accepted by EMNLP 2019

R2 v1 2026-06-23T11:20:05.677Z