论文信息 - Concept Identification and Presentation in the Context of Technical Text Summarization

Concept Identification and Presentation in the Context of Technical Text Summarization

We describe a method of text summarization that produces indicative-informative abstracts for technical papers. The abstracts are generated by a process of conceptual identification, topic extraction and re-generation. We have carried out an evaluation to assess indicativeness and text acceptability relying on human judgment. The results so far indicate good performance in both tasks when compared with other summarization technologies.

Horacio Saggion | Guy Lapalme | G. Lapalme | Horacio Saggion

[1] Regina Barzilay,et al. Using Lexical Chains for Text Summarization , 1997 .

[2] Daniel Marcu,et al. From discourse structures to text summaries , 1997 .

[3] John Greenwood,et al. The Integration of Theory and Practice , 1979 .

[4] Dragomir R. Radev,et al. Generating Natural Language Summaries from Multiple On-Line Sources , 1998, CL.

[5] Inderjeet Mani,et al. The Tipster Summac Text Summarization Evaluation , 1999, EACL.

[6] Timothy Robin Gibson. Towards a discourse theory of abstracts and abstracting , 1993 .

[7] Horacio Saggion,et al. Selective analysis for automatic abstracting: Evaluating Indicativeness and Acceptability , 2000, RIAO.

[8] J. Minel,et al. Résumé automatique par filtrage sémantique d'informations dans des textes , 2001 .

[9] Chris D. Paice,et al. The identification of important concepts in highly structured technical papers , 1993, SIGIR.

[10] Hans Peter Luhn,et al. The Automatic Creation of Literature Abstracts , 1958, IBM J. Res. Dev..

[11] Kathleen McKeown,et al. The decomposition of human-written summary sentences , 1999, SIGIR '99.

[12] Horacio Saggion,et al. Where does Information come from? Corpus Analysis for Automatic Abstracting , 1998 .