Summary: Learning of Graph-based Question Answering Rules
Department of Computing
Sydney 2109, Australia
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 automati-
cally learnt from a training corpus of ques-
tions and answer sentences with the an-
swer annotated. The method is indepen-
dent from the graph representation formal-
ism chosen. A particular example is pre-
sented that uses a specific graph represen-
tation of the logical contents of sentences.