Multi-document summarization by sentence extraction

Goldstein, Jade; Mittal, Vibhu O.; Carbonell, Jaime G.; Kantrowitz, Mark

doi:10.3115/1117575.1117580

Cited by 217 publications

(129 citation statements)

References 18 publications

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…To produce the update summary, some strategies are required to avoid the redundant information which has already been covered by the main summary. One of the most frequently used methods for removing the redundancy is Maximal Marginal Relevance (MMR) [8]. Comparative document summarization is proposed by Wang et al [28] to summarize differences between comparable document groups.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-document summarization via submodularity

2012

Appl Intell

View full text Add to dashboard Cite

Multi-document summarization is becoming an important issue in the Information Retrieval community. It aims to distill the most important information from a set of documents to generate a compressed summary. Given a set of documents as input, most of existing multi-document summarization approaches utilize different sentence selection techniques to extract a set of sentences from the document set as the summary. The submodularity hidden in the term coverage and the textual-unit similarity motivates us to incorporate this property into our solution to multidocument summarization tasks. In this paper, we propose a new principled and versatile framework for different multidocument summarization tasks using submodular functions (Nemhauser et al. in Math. Prog. 14(1): 1978) based on the term coverage and the textual-unit similarity which can be efficiently optimized through the improved greedy algorithm. We show that four known summarization tasks, including generic, query-focused, update, and comparative summarization, can be modeled as different variations derived from the proposed framework. Experiments on benchmark summarization data sets (e.g., DUC04-06, TAC08, TDT2 corpora) are conducted to demonstrate the efficacy and effectiveness of our proposed framework for the general multi-document summarization tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…One of the most popular methods for serving these two purposes is Maximal Marginal Relevance (MMR) [8] which aims to reduce the redundancy and maintain query relevance in retrieved documents at the same time. Hence, a MMR-similar definition for the quality of the current generated summary is given by…”

Section: Textual-unit Similaritymentioning

confidence: 99%

Multi-document summarization via submodularity

2012

Appl Intell

View full text Add to dashboard Cite

show abstract

“…However, to produce a summary automatically is very challenging. Issues such as redundancy, temporal dimension, coreference or sentence ordering, to name a few, have to be taken into consideration especially when summarising a set of documents (multi-document summarisation), thus making this field even more difficult (Goldstein et al 2000). Moreover, research attempting to overcome the lack of coherence that summaries often present has been fuelled in the last years, resulting in combined approaches that identify relevant content and merge it into new fragments of information (Barzilay and McKeown 2005;Zajic et al 2008).…”

Section: Introductionmentioning

confidence: 98%

Text summarisation in progress: a literature review

2011

View full text Add to dashboard Cite

This paper contains a large literature review in the research field of Text Summarisation (TS) based on Human Language Technologies (HLT). TS helps users manage the vast amount of information available, by condensing documents' content and extracting the most relevant facts or topics included in them. The rapid development of emerging technologies poses new challenges to this research field, which still need to be solved. Therefore, it is essential to analyse its progress over the years, and provide an overview of the past, present and future directions, highlighting the main advances achieved and outlining remaining limitations. With this purpose, several important aspects are addressed within the scope of this survey. On the one hand, the paper aims at giving a general perspective on the state-ofthe-art, describing the main concepts, as well as different summarisation approaches, and relevant international forums. Furthermore, it is important to stress upon the fact that the birth of new requirements and scenarios has led to new types of summaries with specific purposes (e.g. sentiment-based summaries), and novel domains within which TS has proven to be also suitable for (e.g. blogs). In addition, TS is successfully combined with a number of intelligent systems based on HLT (e.g. information retrieval, question answering, and text classification). On the other hand, a deep study of the evaluation of summaries is also conducted in this paper, where the existing methodologies and systems are explained, as well as new research that has emerged concerning the automatic evaluation of summaries' quality. Finally, some thoughts about TS in general and its future will encourage the reader to think of novel approaches, applications and lines to conduct research in the next years. The analysis of these issues allows the reader to have a wide and useful background on the main important aspects of this research field.

show abstract

“…Baseline also does not apply any method for the imposing of a redundancy penalty. (d) LIA_THALES applies the maximal-marginalrelevance (MMR) (Carbonell and Goldstein 1998;Goldstein et al 2000) to control sentence redundancy. It runs the MMR on Latent Semantic Analysis (LSA) (Landauer 2002).…”

Section: Discussionmentioning

confidence: 99%

Query-based multi-documents summarization using linguistic knowledge and content word expansion

et al. 2015

View full text Add to dashboard Cite

In this paper, a query-based summarization method, which uses a combination of semantic relations between words and their syntactic composition, to extract meaningful sentences from document sets is introduced. The problem with current statistical methods is that they fail to capture the meaning when comparing a sentence and a user query; hence there is often a conflict between the extracted sentences and users' requirements. However, this particular method can improve the quality of document summaries because it is able to avoid extracting a sentence whose similarity with the query is high but whose meaning is different. The method is executed by computing the semantic and syntactic similarity of the sentence-to-sentence and sentenceto-query. To reduce redundancy in summary, this method uses the greedy algorithm to impose diversity penalty on the sentences. In addition, the proposed method expands the words in both the query and the sentences to tackle the problem of information limit. It bridges the lexical gaps for semantically similar contexts that are expressed using different wording.The experimental results display that the proposed method is able to improve performance compared with the participating systems in DUC 2006. The experimental results also showed that the proposed method demonstrates better performance as compared to other existing techniques on DUC 2005 and DUC 2006 datasets.

show abstract

Multi-document summarization by sentence extraction

Cited by 217 publications

References 18 publications

Multi-document summarization via submodularity

Multi-document summarization via submodularity

Text summarisation in progress: a literature review

Query-based multi-documents summarization using linguistic knowledge and content word expansion

Contact Info

Product

Resources

About