Summarization beyond sentence extraction: a probabilistic approach to sentence compression
Artificial Intelligence
Cut and paste based text summarization
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
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
Manual and automatic evaluation of summaries
AS '02 Proceedings of the ACL-02 Workshop on Automatic Summarization - Volume 4
The Pyramid Method: Incorporating human content selection variation in summarization evaluation
ACM Transactions on Speech and Language Processing (TSLP)
Sentence fusion via dependency graph compression
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Seed and Grow: augmenting statistically generated summary sentences using schematic word patterns
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Exploring content models for multi-document summarization
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Global inference for sentence compression an integer linear programming approach
Journal of Artificial Intelligence Research
On the limits of sentence compression by deletion
Empirical methods in natural language generation
Automatic metrics for genre-specific text quality
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
| Hi-index | 0.00 |
In our work we use an existing classifier to quantify and analyze the level of specific and general content in news documents and their human and automatic summaries. We discover that while human abstracts contain a more balanced mix of general and specific content, automatic summaries are overwhelmingly specific. We also provide an analysis of summary specificity and the summary quality scores assigned by people. We find that too much specificity could adversely affect the quality of content in the summary. Our findings give strong evidence for the need for a new task in abstractive summarization: identification and generation of general sentences.