Query-based sentence fusion is better defined and leads to more preferred results than generic sentence fusion

Authors:
Emiel Krahmer;Erwin Marsi;Paul van Pelt
Affiliations:
Tilburg University, Tilburg, The Netherlands;Tilburg University, Tilburg, The Netherlands;Tilburg University, Tilburg, The Netherlands
Venue:
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Year:
2008

Citing 2
Cited 8

Automatic evaluation of summaries using N-gram co-occurrence statistics

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Sentence Fusion for Multidocument News Summarization

Computational Linguistics

Sentence fusion via dependency graph compression

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Summarizing short stories

Computational Linguistics
Time-efficient creation of an accurate sentence fusion corpus

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Multi-sentence compression: finding shortest paths in word graphs

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Automatic analysis of semantic similarity in comparable text through syntactic tree matching

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Towards strict sentence intersection: decoding and evaluation strategies

MTTG '11 Proceedings of the Workshop on Monolingual Text-To-Text Generation
Learning to fuse disparate sentences

MTTG '11 Proceedings of the Workshop on Monolingual Text-To-Text Generation
Text simplification using typed dependencies: a comparison of the robustness of different generation strategies

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show that question-based sentence fusion is a better defined task than generic sentence fusion (Q-based fusions are shorter, display less variety in length, yield more identical results and have higher normalized Rouge scores). Moreover, we show that in a QA setting, participants strongly prefer Q-based fusions over generic ones, and have a preference for union over intersection fusions.