Year: 2013
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Mendes, Ana Cristina, Coheur, Luísa, Curto, Sérgio
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2396034235