Probabilistic Approaches for Answer Selection in Multilingual Question Answering
Jeongwoo Ko · 2007
question answering To my family for love and support. iv Question answering (QA) aims at finding exact answers to a user’s natural language question from a large collection of documents. Most QA systems combine information retrieval with extraction techniques to identify a set of likely candidates and then utilize some selection strategy to generate the final answers. This selection process can be very challenging, as it often entails ranking the relevant answers to the top positions. To address this challenge, many QA systems have incorporated semantic resources for answer ranking in a single language. However, there has been little research on a generalized probabilistic framework that models the correctness and correlation of answer candidates for multiple languages. In this thesis, we propose two probabilistic models for answer ranking: