Automatic Summarization

Abstract

It has now been 50 years since the publication of Luhn's seminal paper on automatic summarization. During these years the practical need for automatic summarization has become increasingly urgent and numerous papers have been published on the topic. As a result, it has become harder to find a single reference that gives an overview of past efforts or a complete view of summarization tasks and necessary system components. This article attempts to fill this void by providing a comprehensive overview of research in summarization, including the more traditional efforts in sentence extraction as well as the most novel recent approaches for determining important content, for domain and genre specific summarization and for evaluation of summarization. We also discuss 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.

Representative Selection in Nonmetric Datasets

“…The idea of reducing a full set to a smaller set of representatives has been suggested before in specific contexts, such as clustering xml documents [11] or dataset editing [13], and more recently in visual [17,7] and text summarization [28]. It has also been discussed as a general problem in [39].…”

Update summarization: building from scratch for Portuguese and comparing to English

“…The summarization area has traditionally put more efforts on the content selection phase, focusing on producing extractive summaries. The area started with the single document summarization task and evolved to more sophisticated initiatives, as multi-document summarization, including dealing with e-mails, scientific articles, dialogs, speech, and several other media, as discussed in [17]. The update summarization appeared as a type of the multi-document approach and gained a lot of attention due to its usefulness in the current information overload situation that we face nowadays.…”

Automatic text summarisation of case law using gate with annie and summa plug-ins

“…Automatic text summarization is the task of using computers to produce a concise and fluent summary while preserving key information content and overall meaning [10]. The goal of automatic text summarisation is to present the source text as a shorter version with the semantics retained [11,12]; that is to express the contents of a document in a concise and meaningful form that meet user needs. The most important advantage of using a summary instead of the original document is that it saves reading and comprehension time.…”

“…These concerns have sparked interest in the development of automatic summarisation systems or summarisers. Such systems are designed to take one or more documents or information piece and produce a concise and fluent summary of the most important information [11]. Summarisers achieve this by identifying the most important sentences in the input document(s), and stringing them together to form a summary.…”

“…Summarisers achieve this by identifying the most important sentences in the input document(s), and stringing them together to form a summary. Text Summarisation methods can be classified into extractive and abstractive summarisation [10,11,13]. Other classifications include indicative, informative and critical summarizations [12,14].…”