论文信息 - BBN/UMD at DUC-2004: Topiary

BBN/UMD at DUC-2004: Topiary

This paper reports our results at DUC2004 and describes our approach, implemented in a system called Topiary. We will show that the combination of linguistically motivated sentence compression with statistically selected topic terms performs better than either alone, according to some automatic summary evaluation measures.

[1] Ingrid Mårdh,et al. Headlinese : on the grammar of English front page headlines , 1980 .

[2] David D. Lewis,et al. An evaluation of phrasal and clustered representations on a text categorization task , 1992, SIGIR '92.

[3] Richard M. Schwartz,et al. A maximum likelihood model for topic classification of broadcast news , 1997, EUROSPEECH.

[4] Richard M. Schwartz,et al. BBN: Description of the SIFT System as Used for MUC-7 , 1998, MUC.

[5] Daniel Marcu,et al. Statistics-Based Summarization - Step One: Sentence Compression , 2000, AAAI/IAAI.

[6] Timm Euler. Tailoring text using topic words: Selection and compression , 2002, Proceedings. 13th International Workshop on Database and Expert Systems Applications.

[7] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[8] Liang Zhou,et al. Headline Summarization at ISI , 2003 .

[9] Richard M. Schwartz,et al. Cross-language headline generation for Hindi , 2003, TALIP.

[10] Richard M. Schwartz,et al. Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation , 2003, HLT-NAACL 2003.

[11] Richard M. Schwartz,et al. An Algorithm that Learns What's in a Name , 1999, Machine Learning.