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

Hong, Kai; Nenkova, Ani

doi:10.3115/v1/e14-1075

Cited by 105 publications

(90 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also choose as baselines those state-of-the-art summarization results on DUC (2001, 2002, and 2004) data. To our knowledge, the best reported results on DUC 2001DUC , 2002DUC and 2004 are from R2N2 (Cao et al, 2015), ClusterCMRW (Wan and Yang, 2008) and REG-SUM 2 (Hong and Nenkova, 2014) respectively. R2N2 applies recursive neural networks to learn 2 REGSUM truncates a summary to 100 words.…”

Section: Comparison With Baseline Methodsmentioning

confidence: 99%

“…In previous summarization systems, though not well-studied, some widely-used sentence ranking features such as the length and the ratio of stopwords, can be seen as attempts to measure the summary prior nature to a certain extent. Notably, Hong and Nenkova (2014) built a state-of-the-art summarization system through making use of advanced document-independent features. However, these document-independent features are usually hand-crafted, difficult to exhaust each aspect of the summary prior nature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Summary Prior Representation for Extractive Summarization

Cao¹,

Wei²,

Li³

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

102

View full text Add to dashboard Cite

In this paper, we propose the concept of summary prior to define how much a sentence is appropriate to be selected into summary without consideration of its context. Different from previous work using manually compiled documentindependent features, we develop a novel summary system called PriorSum, which applies the enhanced convolutional neural networks to capture the summary prior features derived from length-variable phrases. Under a regression framework, the learned prior features are concatenated with document-dependent features for sentence ranking. Experiments on the DUC generic summarization benchmarks show that PriorSum can discover different aspects supporting the summary prior and outperform state-of-the-art baselines.

show abstract

Section: Comparison With Baseline Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning Summary Prior Representation for Extractive Summarization

Cao¹,

Wei²,

Li³

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

102

View full text Add to dashboard Cite

show abstract

“…Although this dataset has mainly been used to train extractive summarization systems (Hong and Nenkova, 2014;Hong et al, 2015;Li et al, 2016;Durrett et al, 2016), it has recently been used for the abstractive summarization task (Paulus et al, 2018). NYT dataset (Sandhaus, 2008) is a collection of articles published between 1996 and 2007.…”

Section: New York Times (Nyt)mentioning

confidence: 99%

Deep Communicating Agents for Abstractive Summarization

Çelikyılmaz

Bosselut

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

294

253

View full text Add to dashboard Cite

We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.

show abstract

“…As TLS organizes events by date, timelines can be generated by MDS systems (such as (Radev et al, 2004b;Radev et al, 2004a;McKeown et al, 2003;Erkan and Radev, 2004;Metzler and Kanungo, 2008;Hong and Nenkova, 2014) by applying their summarization techniques on news articles for every individual date to create corresponding daily summaries. However, manually written timelines normally only include a small number of dates; in addition, the temporal component imposes constraints on sentence selection for timeline summarization, such as the preference for little overlap between sentences selected for different dates (Yan et al, 2011b).…”

Section: Related Workmentioning

confidence: 99%

Joint Graphical Models for Date Selection in Timeline Summarization

Tran

Herder

Markert

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

Automatic timeline summarization (TLS) generates precise, dated overviews over (often prolonged) events, such as wars or economic crises. One subtask of TLS selects the most important dates for an event within a certain time frame. Date selection has up to now been handled via supervised machine learning approaches that estimate the importance of each date separately, using features such as the frequency of date mentions in news corpora. This approach neglects interactions between different dates that occur due to connections between subevents. We therefore suggest a joint graphical model for date selection. Even unsupervised versions of this model perform as well as supervised state-of-theart approaches. With parameter tuning on training data, it outperforms prior supervised models by a considerable margin.

show abstract

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

Cited by 105 publications

References 30 publications

Learning Summary Prior Representation for Extractive Summarization

Learning Summary Prior Representation for Extractive Summarization

Deep Communicating Agents for Abstractive Summarization

Joint Graphical Models for Date Selection in Timeline Summarization

Contact Info

Product

Resources

About