Proceedings Article10.1145/1148170.1148269
A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization
Ani Nenkova,Lucy Vanderwende,Kathleen McKeown +2 more
- 06 Aug 2006
- pp 573-580
TL;DR: The research shows that a frequency based summarizer can achieve performance comparable to that of state-of-the-art systems, but only with a good composition function; context sensitivity improves performance and significantly reduces repetition.
read more
Abstract: The usual approach for automatic summarization is sentence extraction, where key sentences from the input documents are selected based on a suite of features. While word frequency often is used as a feature in summarization, its impact on system performance has not been isolated. In this paper, we study the contribution to summarization of three factors related to frequency: content word frequency, composition functions for estimating sentence importance from word frequency, and adjustment of frequency weights based on context. We carry out our analysis using datasets from the Document Understanding Conferences, studying not only the impact of these features on automatic summarizers, but also their role in human summarization. Our research shows that a frequency based summarizer can achieve performance comparable to that of state-of-the-art systems, but only with a good composition function; context sensitivity improves performance and significantly reduces repetition.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
Im2Text: Describing Images Using 1 Million Captioned Photographs
Vicente Ordonez,Girish Kulkarni,Tamara L. Berg +2 more
- 12 Dec 2011
TL;DR: A new objective performance measure for image captioning is introduced and methods incorporating many state of the art, but fairly noisy, estimates of image content are developed to produce even more pleasing results.
Determinantal point processes for machine learning
Alex Kulesza,Ben Taskar +1 more
TL;DR: Determinantal Point Processes for Machine Learning provides a comprehensible introduction to DPPs, focusing on the intuitions, algorithms, and extensions that are most relevant to the machine learning community, and shows how they can be applied to real-world applications.
•Book
Automatic Summarization
Ani Nenkova,Sameer Maskey,Yang Liu +2 more
- 27 Jun 2011
TL;DR: The challenges that remain open, in particular the need for language generation and deeper semantic understanding of language that would be necessary for future advances in the field are discussed.
889
Neural Summarization by Extracting Sentences and Words
Jianpeng Cheng,Mirella Lapata +1 more
- 12 Aug 2016
TL;DR: This paper proposed a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor, which achieved state-of-the-art results without any access to linguistic annotation.
A survey of text summarization techniques
Ani Nenkova,Kathleen R. McKeown +1 more
- 01 Jan 2012
TL;DR: This chapter gives a broad overview of existing approaches based on how representation, sentence scoring or summary selection strategies alter the overall performance of the summarizer, and points out some of the peculiarities of the task of summarization.
686
References
•Proceedings Article
ROUGE: A Package for Automatic Evaluation of Summaries
Chin-Yew Lin
- 25 Jul 2004
TL;DR: Four different RouGE measures are introduced: ROUGE-N, ROUge-L, R OUGE-W, and ROUAGE-S included in the Rouge summarization evaluation package and their evaluations.
The automatic creation of literature abstracts
TL;DR: In the exploratory research described, the complete text of an article in machine-readable form is scanned by an IBM 704 data-processing machine and analyzed in accordance with a standard program.
3.5K
The Use of MMR and Diversity-Based Reranking for Reodering Documents and Producing Summaries
Jaime G. Carbonell,Jade Goldstein +1 more
- 01 Jan 1998
TL;DR: The MaximalMarginal Relevance (MMR) criterion as mentioned in this paper aims to reduce redundancy while maintaining query relevance in retrieving retrieved documents and selecting appropriate passages for text summarization.
The use of MMR, diversity-based reranking for reordering documents and producing summaries
Jaime Carbinell,Jade Goldstein +1 more
- 01 Aug 1998
TL;DR: A method for combining query-relevance with information-novelty in the context of text retrieval and summarization and preliminary results indicate some benefits for MMR diversity ranking in document retrieval and in single document summarization.
Automatic evaluation of summaries using N-gram co-occurrence statistics
Chin-Yew Lin,Eduard Hovy +1 more
- 27 May 2003
TL;DR: The results show that automatic evaluation using unigram co-occurrences between summary pairs correlates surprising well with human evaluations, based on various statistical metrics; while direct application of the BLEU evaluation procedure does not always give good results.
Related Papers (5)
Chin-Yew Lin
- 25 Jul 2004
Rada Mihalcea,Paul Tarau +1 more
- 01 Jul 2004
Julian M. Kupiec,Jan O. Pedersen,Francine Chen +2 more
- 01 Jul 1995