A Split-and-Recombine Approach for Follow-up Query Analysis
This addresses the problem of handling multifarious follow-up scenarios in semantic parsing for domains like dialogue systems, but it is incremental as it builds on existing context-independent parsing advances.
The paper tackles the challenge of context-dependent semantic parsing by proposing a split-and-recombine approach (STAR) for follow-up query analysis, which restates queries with contextual information and outperforms the state-of-the-art baseline by nearly 8% on the FollowUp dataset.
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.