Improving the Estimation of Word Importance for News Multi-Document Summarization

@inproceedings{Hong2014ImprovingTE,
  title={Improving the Estimation of Word Importance for News Multi-Document Summarization},
  author={Kai Hong and A. Nenkova},
  booktitle={EACL},
  year={2014}
}
In this paper, we propose a supervised model for ranking word importance that incorporates a rich set of features. Our model is superior to prior approaches for identifying words used in human summaries. Moreover we show that an extractive summarizer which includes our estimation of word importance results in summaries comparable with the state-of-the-art by automatic evaluation. Disciplines Computer Engineering | Computer Sciences Comments University of Pennsylvania Department of Computer and… Expand
Content selection in multi-document summarization
What's Important in a Text? An Extensive Evaluation of Linguistic Annotations for Summarization
Recent automatic text summarization techniques: a survey
Recent advances in document summarization
Multi-Document Summarization and Semantic Relatedness
Which Scores to Predict in Sentence Regression for Text Summarization?
Learning to Estimate the Importance of Sentences for Multi-Document Summarization
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 54 REFERENCES
The Impact of Frequency on Summarization
Measuring Importance and Query Relevance in Topic-focused Multi-document Summarization
Exploring Content Models for Multi-Document Summarization
Extractive Multi-Document Summaries Should Explicitly Not Contain Document Specific Content
Topic-Focused Multi-Document Summarization Using an Approximate Oracle Score
Multi-Document Summarization by Maximizing Informative Content-Words
Jointly Learning to Extract and Compress
...
1
2
3
4
5
...