Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters
This work addresses a key challenge in semantic parsing for table-based question answering, though it is incremental as it builds on existing pointer-generator methods.
The authors tackled the problem of translating natural language to SQL queries by extending a pointer-generator network and investigating decoding order issues, achieving competitive performance on WikiSQL compared to more complex models.
Translating natural language to SQL queries for table-based question answering is a challenging problem and has received significant attention from the research community. In this work, we extend a pointer-generator and investigate the order-matters problem in semantic parsing for SQL. Even though our model is a straightforward extension of a general-purpose pointer-generator, it outperforms early works for WikiSQL and remains competitive to concurrently introduced, more complex models. Moreover, we provide a deeper investigation of the potential order-matters problem that could arise due to having multiple correct decoding paths, and investigate the use of REINFORCE as well as a dynamic oracle in this context.