Imitating human literature review writing: an approach to multi-document summarization

Authors:
Kokil Jaidka;Christopher Khoo;Jin-Cheon Na
Affiliations:
Wee Kim Wee School of Communication and Information, Nanyang Technological University, Singapore;Wee Kim Wee School of Communication and Information, Nanyang Technological University, Singapore;Wee Kim Wee School of Communication and Information, Nanyang Technological University, Singapore
Venue:
ICADL'10 Proceedings of the role of digital libraries in a time of global change, and 12th international conference on Asia-Pacific digital libraries
Year:
2010

Citing 5
Cited 1

Generating indicative-informative summaries with sumUM

Computational Linguistics - Summarization
Experiments in multidocument summarization

HLT '02 Proceedings of the second international conference on Human Language Technology Research
Design and development of a concept-based multi-document summarization system for research abstracts

Journal of Information Science
Multi-document summarization by sentence extraction

NAACL-ANLP-AutoSum '00 Proceedings of the 2000 NAACL-ANLP Workshop on Automatic Summarization
Arabic/English multi-document summarization with CLASSY: the past and the future

CICLing'08 Proceedings of the 9th international conference on Computational linguistics and intelligent text processing

Towards automated related work summarization

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper gives an overview of a project to generate literature reviews from a set of research papers, based on techniques drawn from human summarization behavior. For this study, we identify the key features of natural literature reviews through a macro-level and clause-level discourse analysis; we also identify human information selection strategies by mapping referenced information to source documents. Our preliminary results of discourse analysis have helped us characterize literature review writing styles based on their document structure and rhetorical structure. These findings will be exploited to design templates for automatic content generation.