You are here

Learning of graph-based question answering rules

TitleLearning of graph-based question answering rules
Publication TypeConference Paper
Year of Publication2006
AuthorsMoll√°, D
Conference NameFirst Workshop on Graph Based Methods for Natural Language Processing
PublisherAssociation for Computational Linguistics
Conference LocationNew York City, NY

In this paper we present a graph-based approach to question answering. The method assumes a graph representation of question sentences and text sentences. Question answering rules are automatically learnt from a training corpus of questions and answer sentences with the answer annotated. The method is independent from the graph representation formalism chosen. A particular example is presented that uses a specific graph representation of the logical contents of sentences.