Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts

Schluter, Natalie; Søgaard, Anders

doi:10.3115/v1/p15-2138

Cited by 20 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 The test set consists of 111 pairs. We use the same summary budget of 335 used by Schluter and Søgaard (2015).…”

Section: Rouge-n(s) :=mentioning

confidence: 99%

See 1 more Smart Citation

The limits of automatic summarisation according to ROUGE

Schluter¹

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 2

Self Cite

View full text Add to dashboard Cite

This paper discusses some central caveats of summarisation, incurred in the use of the ROUGE metric for evaluation, with respect to optimal solutions. The task is NPhard, of which we give the first proof. Still, as we show empirically for three central benchmark datasets for the task, greedy algorithms empirically seem to perform optimally according to the metric. Additionally, overall quality assurance is problematic: there is no natural upper bound on the quality of summarisation systems, and even humans are excluded from performing optimal summarisation.

show abstract

“…4 The test set consists of 111 pairs. We use the same summary budget of 335 used by Schluter and Søgaard (2015).…”

Section: Rouge-n(s) :=mentioning

confidence: 99%

“…3 The test set consists of 138 pairs. We adopt the same summary budget length: 805 words used by Schluter and Søgaard (2015). wiki: Wikipedia leading paragraphs-article pairs (all labeled "good article") from a comprehensive dump of English language Wikipedia articles.…”

Section: Rouge-n(s) :=mentioning

confidence: 99%

The limits of automatic summarisation according to ROUGE

Schluter¹

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 2

Self Cite

View full text Add to dashboard Cite

show abstract

“…The same idea was followed by many researches (Woodsend and Lapata 2012; Li, Qian, and Liu 2013). Recently, (Schluter and Søgaard 2015) reported that syntactic and semantic concepts might also be helpful, and some papers such as (Cao et al 2015a) combined sentence and concept selection process. With heuristic rules, ILP can apply to compress (Gillick and Favre 2009;Berg-Kirkpatrick, Gillick, and Klein 2011) or even fuse (Bing et al 2015).…”

Section: Ilp For Summarizationmentioning

confidence: 99%

TGSum: Build Tweet Guided Multi-Document Summarization Dataset

Cao

Chen

et al. 2017

Social Media Content Analysis

View full text Add to dashboard Cite

The development of summarization research has been significantly hampered by the costly acquisition of reference summaries. This paper proposes an effective way to automatically collect large scales of news-related multi-document summaries with reference to social media's reactions. We utilize two types of social labels in tweets, i.e., hashtags and hyper-links. Hashtags are used to cluster documents into different topic sets. Also, a tweet with a hyper-link often highlights certain key points of the corresponding document. We synthesize a linked document cluster to form a reference summary which can cover most key points. To this aim, we adopt the ROUGE metrics to measure the coverage ratio, and develop an Integer Linear Programming solution to discover the sentence set reaching the upper bound of ROUGE. Since we allow summary sentences to be selected from both documents and highquality tweets, the generated reference summaries could be abstractive. Both informativeness and readability of the collected summaries are verified by manual judgment. In addition, we train a Support Vector Regression summarizer on DUC generic multi-document summarization benchmarks. With the collected data as extra training resource, the performance of the summarizer improves a lot on all the test sets. We release this dataset for further research 1 .

show abstract

“…There were mainly two categories for automatic text summarization: extractive summarization and abstractive summarization [14,15]. The prior one aimed to identify summary sentences or summary words from a document that was a good description of the bones of the document before placing them in order [16][17][18]. In comparison, the latter one was not constrained by using the original sentences or words in the document and could generate a more abstractive summary [19][20][21].…”

Section: Automatic Text Summarizationmentioning

confidence: 99%

Identifying High Quality Document–Summary Pairs through Text Matching

Hou¹,

Xiang²,

Tang³

et al. 2017

Information

View full text Add to dashboard Cite

Text summarization namely, automatically generating a short summary of a given document, is a difficult task in natural language processing. Nowadays, deep learning as a new technique has gradually been deployed for text summarization, but there is still a lack of large-scale high quality datasets for this technique. In this paper, we proposed a novel deep learning method to identify high quality document-summary pairs for building a large-scale pairs dataset. Concretely, a long short-term memory (LSTM)-based model was designed to measure the quality of document-summary pairs. In order to leverage information across all parts of each document, we further proposed an improved LSTM-based model by removing the forget gate in the LSTM unit. Experiments conducted on the training set and the test set built upon Sina Weibo (a Chinese microblog website similar to Twitter) showed that the LSTM-based models significantly outperformed baseline models with regard to the area under receiver operating characteristic curve (AUC) value.

show abstract

Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts

Cited by 20 publications

References 8 publications

The limits of automatic summarisation according to ROUGE

The limits of automatic summarisation according to ROUGE

TGSum: Build Tweet Guided Multi-Document Summarization Dataset

Identifying High Quality Document–Summary Pairs through Text Matching

Contact Info

Product

Resources

About