Hedge Trimmer

Dorr, Bonnie J.; Zajic, David; Schwartz, Richard

doi:10.3115/1119467.1119468

Cited by 155 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DUC summaries are often used in conjunction with larger training datasets, including Gigaword (Rush et al, 2015;Chopra et al, 2016), CNN / Daily Mail (Nallapati et al, 2017;Paulus et al, 2017;See et al, 2017), or Daily Mail alone (Nallapati et al, 2016b;Cheng and Lapata, 2016). The data have also been used to evaluate unsupervised methods (Dorr et al, 2003;Mihalcea and Tarau, 2004;Barrios et al, 2016).…”

Section: Document Understanding Conferencementioning

confidence: 99%

See 1 more Smart Citation

Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies

Grusky¹,

Нааман²,

Artzi³

2018

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

402

452

View full text Add to dashboard Cite

We present NEWSROOM, a summarization dataset of 1.3 million articles and summaries written by authors and editors in newsrooms of 38 major news publications. Extracted from search and social media metadata between 1998 and 2017, these high-quality summaries demonstrate high diversity of summarization styles. In particular, the summaries combine abstractive and extractive strategies, borrowing words and phrases from articles at varying rates. We analyze the extraction strategies used in NEWSROOM summaries against other datasets to quantify the diversity and difficulty of our new data, and train existing methods on the data to evaluate its utility and challenges. The dataset is available online at summari.es.

show abstract

Section: Document Understanding Conferencementioning

confidence: 99%

“…When used this way, Gigaword's simulated summaries are shorter than most natural summary text. Gigaword, along with similar text-headline datasets (Filippova and Altun, 2013), are also used for the related sentence compression task (Dorr et al, 2003;Filippova et al, 2015).…”

Section: Gigawordmentioning

confidence: 99%

Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies

Grusky¹,

Нааман²,

Artzi³

2018

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

402

452

View full text Add to dashboard Cite

show abstract

“…These methods apply handcrafted linguistic rules to extract or compress important sentences in a document [21]. They are simple and lightweight; however, they fail to understand complex relationships in the text, and it is not easy to prepare templates for them.…”

Section: Template-based Approachesmentioning

confidence: 99%

On Implementing an Automatic Headline Generation for Discussion BBS Systems —Cases of Citizens' Deliberations for Communities—

Fujita

Watanabe

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Recently, the opportunity to discuss topics on a variety of online discussion bulletin boards has been increasing. However, it can be difficult to understand the contents of each discussion as the number of posts increases. Therefore, it is important to generate headlines that can automatically summarize each post in order to understand the contents of each discussion at a glance. In this paper, we propose a method to extract and generate post headlines for online discussion bulletin boards, automatically. We propose templates with multiple patterns to extract important sentences from the posts. In addition, we propose a method to generate headlines by matching the templates with the patterns. Then, we evaluate the effectiveness of our proposed method using questionnaires. key words: automated headline generation, electronic discussion bulletin boards, natural language processing

show abstract

“…Among the four summarization techniques compared by Mohammad et al (2009), the best at capturing the contributions of papers was Multi-Document Trimmer (MDT) (Zajic, Dorr, Schwartz, Monz, & Lin, 2005;Zajic, Dorr, Lin, & Schwartz, 2007), originally designed to summarize news articles. MDT is an extension of the original Trimmer that summarized single news articles (Dorr, Zajic, & Schwartz, 2003;Zajic, Dorr, & Schwartz, 2004). ASE uses MDT to provide summaries of citation text, but because citation sentences have metadata inline, we made some modifications to better handle this data.…”

Section: Multi-document Summarizationmentioning

confidence: 99%

Rapid understanding of scientific paper collections: Integrating statistics, text analytics, and visualization

Dunne

Shneiderman

Gove

et al. 2012

J Am Soc Inf Sci Tec

Self Cite

View full text Add to dashboard Cite

Keeping up with rapidly growing research fields, especially when there are multiple interdisciplinary sources, requires substantial effort for researchers, program managers, or venture capital investors. Current theories and tools are directed at finding a paper or website, not gaining an understanding of the key papers, authors, controversies, and hypotheses. This report presents an effort to integrate statistics, text analytics, and visualization in a multiple coordinated window environment that supports exploration. Our prototype system, Action Science Explorer (ASE), provides an environment for demonstrating principles of coordination and conducting iterative usability tests of them with interested and knowledgeable users. We developed an understanding of the value of reference management, statistics, citation text extraction, natural language summarization for single and multiple documents, filters to interactively select key papers, and network visualization to see citation patterns and identify clusters. A three‐phase usability study guided our revisions to ASE and led us to improve the testing methods.

show abstract

Hedge Trimmer

Cited by 155 publications

References 15 publications

Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies

Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies

On Implementing an Automatic Headline Generation for Discussion BBS Systems —Cases of Citizens' Deliberations for Communities—

Rapid understanding of scientific paper collections: Integrating statistics, text analytics, and visualization

Contact Info

Product

Resources

About