Relevant Information Extraction Driven with Rhetorical Schemas to Summarize Scientific Papers

Authors:
Mariem Ellouze;Abdelmajid Ben Hamadou
Affiliations:
-;-
Venue:
PorTAL '02 Proceedings of the Third International Conference on Advances in Natural Language Processing
Year:
2002

Citing 3
Cited 0

Constructing literature abstracts by computer: techniques and prospects

Information Processing and Management: an International Journal - Special issue on natural language processing and information retrieval
A trainable document summarizer

SIGIR '95 Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval
Enhancing Readability of Automatic Summaries by Using Schemas

TSD '99 Proceedings of the Second International Workshop on Text, Speech and Dialogue

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic summaries are often subject to several criticisms (e.g., lack of cohesion and coherence). In this paper, we propose an approach that uses coherent Summary-Schemas (templates) conceived from the rhetorical structure of scientific papers including their abstracts. The Summary-Schemas embed rhetorical roles specified by signatures (sets of positional, structural, linguistic and thematic features) that guide the search for appropriate sentences in the source text.