Learning Discourse-Level Structures for Question Answering

Abstract

Traditional parse trees are combined together and enriched with anaphora and rhetoric information to form a unified representation for a paragraph of text. We refer to these representations as parse thickets. They are introduced to support answering complex questions, which include multiple sentences, to tackle as many constraints expressed in this question as possible. The question answering system is designed so that an initial set of answers, which is obtained by a TF*IDF or other keyword search model, is re-ranked. Passage re-ranking is performed using matching of the parse thickets of answers with the parse thicket of the question. To do that, a graph representation and matching technique for parse structures for paragraphs of text have been developed. We define the operation of generalization of two parse thickets as a measure of semantic similarity between paragraphs of text to be the maximal common sub-thicket of these parse thickets.