Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
This addresses the problem of building transferable NLIs for databases, which is crucial for industrial applications, but it appears incremental as it builds on existing methods for domain adaptation.
The paper tackled domain adaptation for natural language interfaces to structured queries with limited target domain data by proposing a Structured Query Inference Network for better semantic parsing and a GAN-based augmentation technique, achieving state-of-the-art results on datasets like GeoQuery, Overnight, and WikiSQL.
A natural language interface (NLI) to structured query is intriguing due to its wide industrial applications and high economical values. In this work, we tackle the problem of domain adaptation for NLI with limited data on target domain. Two important approaches are considered: (a) effective general-knowledge-learning on source domain semantic parsing, and (b) data augmentation on target domain. We present a Structured Query Inference Network (SQIN) to enhance learning for domain adaptation, by separating schema information from NL and decoding SQL in a more structural-aware manner; we also propose a GAN-based augmentation technique (AugmentGAN) to mitigate the issue of lacking target domain data. We report solid results on GeoQuery, Overnight, and WikiSQL to demonstrate state-of-the-art performances for both in-domain and domain-transfer tasks.