LCC’s GISTexter at DUC 2006: Multi-Strategy Multi-Document Summarization
نویسندگان
چکیده
In this paper, we describe how Language Computer Corporation’s GISTEXTER question-directed summarization system combines multiple strategies for question decomposition and summary generation in order to produce summary-length answers to complex questions. In addition, we introduce a novel framework for question-directed summarization that uses a state-of-the-art textual entailment system (Hickl et al., 2006) in order to select a single responsive summary answer from amongst a number of candidate summaries. We show that by considering entailment relationships between sentences extracted for a summary, we can automatically create semantic “Pyramids” that can be used to identify answer passages that are both relevant and responsive.
منابع مشابه
Lite - GISTexter at DUC 2005
This paper describes how Language Computer Corporation’s Lite-GISTexter multi-document summarization system addresses the challenge of providing summary-length answers to the types of complex questions asked in DUC 2005. We show that techniques first used in the automatic answering of “relationship” questions can be used in multi-document summarization in order to provide accurate and responsiv...
متن کاملMultidocument Summarization with GISTexter
This paper presents the architecture and the multidocument summarization techniques implemented in the GISTEXTER system. The paper presents an algorithm for producing incremental multi-document summaries if extraction templates of good quality are available. An empirical method of generating ad-hoc templates that can be populated with information extracted from texts by automatically acquired e...
متن کاملQuery Focus Guided Sentence Selection Strategy for DUC 2006
This paper presents our new query-based multi-document summarization system for DUC 2006. It is an extended version of a generic multi-document summarization system developed previously (namely PoluS 1.0) which incorporates latent semantic analysis (LSA) technology. To make the generated summaries satisfying user’s information need as possible as we can, we propose a query focus guided sentence...
متن کاملBuilding a Trainable Multi-document Summarizer
This paper describes an approach to building a trainable multi-document summarization system, using a simple training process based on support vector machines. The summarization system is trained and tested using the DUC 2005 data set. The evaluation results based on ROUGE scores are presented and methods for improving the performance of the summarization system are identified.
متن کاملGenerating Single and Multi-Document Summaries with GISTEXTER
This paper presents the techniques implemented in GISTEXTER for producing extracts and abstracts from both single and multiple documents. These techniques promote the belief that highly coherent summaries may be generated when using textual information identified by the Information Extraction technology. The results of GISTEXTER in the DUC-2002 evaluations account for the advantages of using th...
متن کامل