Back to Search Start Over

Answering Complex Questions with Random Walk Models.

Authors :
Harabagiu, Sanda
Lacatusu, Finley
Hickl, Andrew
Source :
SIGIR Forum; 2006 Proceedings, Vol. 39, p220-227, 8p, 2 Diagrams, 9 Charts, 3 Graphs
Publication Year :
2006

Abstract

We present a novel framework for answering complex questions that relies on question decomposition. Complex questions are decomposed by a procedure that operates on a Markov chain, by following a random walk on a bipartite graph of relations established between concepts related to the topic of a complex question and subquestions derived from topic-relevant passages that manifest these relations. Decomposed questions discovered during this random walk are then submitted to a state-of-the-art Question Answering (Q/A) system in order to retrieve a set of passages that can later be merged into a comprehensive answer by a Multi-Document Summarization (MDS) system. In our evaluations, we show that access to the decompositions generated using this method can significantly enhance the relevance and comprehensiveness of summary length answers to complex questions. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
01635840
Volume :
39
Database :
Complementary Index
Journal :
SIGIR Forum
Publication Type :
Periodical
Accession number :
22879701