Question Answering over Structured Data: an Entailment-Based Approach to Question Analysis

This paper addresses question analysis in the framework of Question Answering over structured data. The problem is set as a relation extraction task, where all the relations of interest in a given domain have to be extracted from natural language questions. The proposed approach applies the notion of Textual Entailment to compare the input questions with a repository of relational textual patterns. The underlying assumption is that a question expresses a certain relation if a pattern for that relation is entailed by the question. We report on a number of experiments, testing different simple distancebased entailment algorithms over a dataset of 1487 English questions covering the domain of cultural events in a town, and 75 relations that are relevant in this domain. The positive results obtained demonstrate the feasibility of the overall approach, and its effectiveness in the proposed