A Generate-Validate Approach to Answering Questions about Qualitative Relationships
This addresses the challenge of transfer learning in semantic parsing for question answering, particularly in chatbots or voice agents, though it is incremental as it builds on existing approaches.
The paper tackled the problem of answering questions about qualitative relationships by proposing a generate-validate framework that replaces direct semantic parsing with generating natural language descriptions and validating them against input text, resulting in a 7.93% improvement over state-of-the-art methods.
Qualitative relationships describe how increasing or decreasing one property (e.g. altitude) affects another (e.g. temperature). They are an important aspect of natural language question answering and are crucial for building chatbots or voice agents where one may enquire about qualitative relationships. Recently a dataset about question answering involving qualitative relationships has been proposed, and a few approaches to answer such questions have been explored, in the heart of which lies a semantic parser that converts the natural language input to a suitable logical form. A problem with existing semantic parsers is that they try to directly convert the input sentences to a logical form. Since the output language varies with each application, it forces the semantic parser to learn almost everything from scratch. In this paper, we show that instead of using a semantic parser to produce the logical form, if we apply the generate-validate framework i.e. generate a natural language description of the logical form and validate if the natural language description is followed from the input text, we get a better scope for transfer learning and our method outperforms the state-of-the-art by a large margin of 7.93%.