Abstract

Selecting important information while accounting for repetitions is a hard task for both summarization and question answering. We propose a formal model that represents a collection of documents in a two-dimensional space of textual and conceptual units with an associated mapping between these two dimensions. This representation is then used to describe the task of selecting textual units for a summary or answer as a formal optimization task. We provide approximation algorithms and empirically validate the performance of the proposed model when used with two very different sets of features, words and atomic events. 1

Citations

443	The Automatic Creation of Literature Abstracts. IBM Journal of Research and Development - Luhn - 1958
276	Using lexical chains for text summarization - Barzilay, Elhadad - 1997
260	and E.Hovy. Automatic Evaluation of Summaries Using N-gram Co-Occurrence Statistics - Lin - 2003
190	New Methods in Automatic Extracting - Edmundson - 1969
116	From discourse structures to text summaries - Marcu - 1997
83	Sentence extraction as a classification task - Teufel, Moens
71	Identifying topics by position - Lin, Hovy - 1997
62	Simfinder: A Flexible Clustering Tool for Summarization - Hatzivassiloglou, Klavans, et al. - 2001
48	Approximating covering and packing problems: set cover, independent set, and related problems, in Approximation Algorithms for NP-Hard Problems - Hochbaum - 1997
39	Creating and Evaluating Multi-document Sentence Extract Summaries - Goldstein, Mittal, et al. - 2000
21	Evaluating answers to definition questions - Voorhees - 2003
2	Defscriber: A hybrid system for definitional qa - Blair-Goldenshon, McKeown, et al. - 2003
2	detection, extraction, and labeling of atomic events - Domain-independent