Learning of Graph-based Question Answering Rules
Proc. HLT/NAACL 2006 Workshop on Graph Algorithms for Natural Language Processing, page 37-44. (2006)Abstract
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.