Towards Interactive Question Answering: An Ontology-Based Approach

The ability to provide both rich and natural answers with respect to a given question, and clear explanations for failures, is a crucial aspect for a future generation of Question Answering systems able to interact with a user. We argue that such abilities are necessarily based on a deep analysis of the content of both the question and the answer, and propose an ontology-based approach to represent the structure of a question-answer pair in the context of utterance. The approach is domain and language-independent and can be considered a general framework for both Open Domain Question Answering and Natural Language Interfaces to Databases. We provide definitions for an Interactive Question Answer (IQA) ontology which capture significant aspects of interaction, and suggest how dialogue templates based on the IQA ontology can model natural and rich dialogues with a user.