Satisfying information needs with multi-document summaries

被引:29
作者
Harabagiu, Sanda
Hickl, Andrew [1 ]
Lacatusu, Finley
机构
[1] Language Comp Corp, Richardson, TX 75080 USA
[2] Univ Texas, Human Language Technol Res Inst, Richardson, TX 75083 USA
关键词
Question decomposition; Summarization; Textual entailment;
D O I
10.1016/j.ipm.2007.01.004
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Generating summaries that meet the information needs of a user relies on (1) several forms of question decomposition; (2) different summarization approaches; and (3) textual inference for combining the summarization strategies. This novel framework for summarization has the advantage of producing highly responsive summaries, as indicated by the evaluation results. (C) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1619 / 1642
页数:24
相关论文
共 25 条
[1]  
Bar-Haim Roy, 2006, P 2 PASCAL CHALL WOR
[2]  
BARZILAY R, 2003, HLT NAACL
[3]  
CLIFTON T, 2004, P 13 TEXT RETR C
[4]  
Dagan I., 2005, P PASCAL CHALL WORKS
[5]  
HARABAGIU S, 2003, P 12 TEXT RETR C
[6]  
HARABAGIU S, 2004, P 20 COLING C GEN SW
[7]  
HARABAGIU S, 2001, P 10 TEXT RETR C
[8]  
HARABAGIU S, 2005, P 14 TEXT RETR C
[9]  
Harabagiu Sanda M., 2005, P 43 ANN M ASS COMP
[10]  
HICKL A, 2006, P 2 PASCAL REC TEXT