Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions
This is a survey paper that addresses the incremental challenge of improving QA systems for geographic questions, which is important for users needing spatial information.
The paper tackles the problem of geographic question answering (GeoQA), highlighting its challenges and uniqueness compared to general QA, and provides a classification framework and future research directions.
As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial operations. In this paper, we discuss the problem of geographic question answering (GeoQA). We first investigate the reasons why geographic questions are difficult to answer by analyzing challenges of geographic questions. We discuss the uniqueness of geographic questions compared to general QA. Then we review existing work on GeoQA and classify them by the types of questions they can address. Based on this survey, we provide a generic classification framework for geographic questions. Finally, we conclude our work by pointing out unique future research directions for GeoQA.