Comparing topiary-style approaches to headline generation
作者： Ruichao Wang , Nicola Stokes , William P. Doran , Eamonn Newman , Joe Carthy
DOI: 10.1007/978-3-540-31865-1_12
关键词: Topiary 、 Noun phrase 、 Proper noun 、 Computer science 、 Headline 、 Artificial intelligence 、 Natural language processing 、 Structure (mathematical logic) 、 Phrase 、 Sentence
摘要: In this paper we compare a number of Topiary-style headline generation systems. The Topiary system, developed at the University Maryland with BBN, was top performing system DUC 2004. headlines consist general topic labels followed by compressed version lead sentence news story. uses statistical learning approach to finding for headlines, while our approach, LexTrim identifies key summary words analysing lexical cohesive structure text. performance these systems is evaluated using ROUGE evaluation suite on 2004 stories collection. results experiments show that baseline descriptors term frequency counts outperforms and A manual also confirms result.
core.ac.uk
ucd.ie
springer.com
sci-hub.st 参考文章(21)
Liang Zhou, Headline Summarization at ISI ,(2003)
Wessel Kraaij, Martijn Spitters, Anette Hulth, Headline extraction based on a combination of uni- and multidocument summarization techniques ,(2002)
John Dunnion, Joe Carthy, Fergus Toolan, William Doran, Eamonn Newman, Nicola Stokes, News Story Gisting at University College Dublin ,(2004)
Eduard Hovy, Liang Zhou, Template-Filtered Headline Summarization Text Summarization Branches Out. pp. 56- 60 ,(2004)
Michael Crystal, Lance Ramshaw, Richard Schwartz, Heidi Fox, Rebecca Stone, Scott Miller, Ralph Weischedel, BBN: Description of the SIFT System as Used for MUC-7 Seventh Message Understanding Conference (MUC-7): Proceedings of a Conference Held in Fairfax, Virginia, April 29 - May 1, 1998. ,(1998)
Vibhu O. Mittal, Michael J. Witbrock, Ultra-Summarization: A Statistical Approach to Generating Highly Condensed Non-Extractive Summaries (poster abstract). international acm sigir conference on research and development in information retrieval. pp. 315- 316 ,(1999)
Jinxi Xu, John Broglio, Bruce Croft, The Design and Implementation of a Part of Speech Tagger for English University of Massachusetts. ,(1994)
Nicola Stokes, Eamonn Newman, Joe Carthy, Alan F. Smeaton, Broadcast News Gisting Using Lexical Cohesion Analysis Lecture Notes in Computer Science. pp. 209- 222 ,(2004) , 10.1007/978-3-540-24752-4_16
Graeme Hirst, Jane Morris, Lexical cohesion computed by thesaural relations as an indicator of the structure of text Computational Linguistics. ,vol. 17, pp. 21- 48 ,(1991)
Michael Collins, Three generative, lexicalised models for statistical parsing Proceedings of the 35th annual meeting on Association for Computational Linguistics -. pp. 16- 23 ,(1997) , 10.3115/976909.979620