Learning to answer questions
This work addresses question answering for users needing accurate responses, but it is incremental as it builds on existing answer-extraction methods.
The paper tackles open-domain question answering by learning lexico-syntactic patterns from past interactions to extract answers, resulting in improved system performance when combined with typical strategies and enabling learning from and correction of past questions.
We present an open-domain Question-Answering system that learns to answer questions based on successful past interactions. We follow a pattern-based approach to Answer-Extraction, where (lexico-syntactic) patterns that relate a question to its answer are automatically learned and used to answer future questions. Results show that our approach contributes to the system's best performance when it is conjugated with typical Answer-Extraction strategies. Moreover, it allows the system to learn with the answered questions and to rectify wrong or unsolved past questions.