Neural Semantic Parsing over Multiple Knowledge-bases
This addresses the problem of data scarcity in semantic parsing for natural language processing researchers, offering a method to improve accuracy and efficiency across multiple domains, though it is incremental as it builds on existing sequence-to-sequence approaches.
The paper tackles the challenge of limited supervision for semantic parsers by training a single sequence-to-sequence model over multiple knowledge-bases, sharing information across domains. It achieves state-of-the-art performance on the Overnight dataset, improving accuracy from 75.6% to 79.6% with a 7x reduction in model parameters.
A fundamental challenge in developing semantic parsers is the paucity of strong supervision in the form of language utterances annotated with logical form. In this paper, we propose to exploit structural regularities in language in different domains, and train semantic parsers over multiple knowledge-bases (KBs), while sharing information across datasets. We find that we can substantially improve parsing accuracy by training a single sequence-to-sequence model over multiple KBs, when providing an encoding of the domain at decoding time. Our model achieves state-of-the-art performance on the Overnight dataset (containing eight domains), improves performance over a single KB baseline from 75.6% to 79.6%, while obtaining a 7x reduction in the number of model parameters.