A Gradual Combination of Features for Building Automatic Summarisation Systems

Lloret, Elena; Palomar, Manuel

doi:10.1007/978-3-642-04208-9_6

Cited by 27 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first mention to text summarization sentence evaluation dates back to 1958 [26] [27]. As antecedently given, the main focus of those analysis area units are self-addressed by the subsequent question: however will a system fix that sentences are symbolic of the content of a given text?…”

Section: Sentence Evaluation Methodsmentioning

confidence: 99%

A Survey of Relevant Text Content Summarization Techniques

2016

IJSR

View full text Add to dashboard Cite

With lots of information getting generated every day, document summarization is becoming essential. Instead of having to go through the entire text, it is convenient to understand the text fast and easily by a relevant summery. [1] Text summarization is the procedure of automatically making a shorter version of one or more text documents. It is a significant method of detection related material in huge text libraries or in the Internet [2]. It is also important to extract the information is such a manner that the content would be of interest of the user. This paper covers various techniques that are used for relevant content summarization.

show abstract

Section: Sentence Evaluation Methodsmentioning

confidence: 99%

A Survey of Relevant Text Content Summarization Techniques

2016

IJSR

View full text Add to dashboard Cite

show abstract

“…This weight will indicate how relevant the sentence is (its score), thus determining which sentences are to be selected and extracted in the final stage (sentence selection). The effectiveness of such modules for TS has been shown in previous research, 58 but the two main stages of the TS process (redundancy removal and relevance detection) are next explained in more detail.…”

Section: The Initial Approach To Text Summarizationmentioning

confidence: 98%

“…These summaries were generated employing, as a basis, the generic TS approach described in Ref. 58 and adapting it to a QF summarization approach, since it has been proven that this type of summarization is more appropriate for QA tasks. 56 In the following subsections, the initial QA and TS approaches are first described independently, and then the proposed TS-QA combination is explained in more detail.…”

Section: Our Approach: Text Summarization-question Answeringmentioning

confidence: 99%

Text summarization contribution to semantic question answering: New approaches for finding answers on the web

Lloret

Llorens

Moreda

et al. 2011

Int. J. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

As the Internet grows, it becomes essential to find efficient tools to deal with all the available information. Question answering (QA) and text summarization (TS) research fields focus on presenting the information requested by users in a more concise way. In this paper, the appropriateness and benefits of using summaries in semantic QA are analyzed. For this purpose, a combined approach where a TS component is integrated into a Web-based semantic QA system is developed. The main goal of this paper is to determine to what extent TS can help semantic QA approaches, when using summaries instead of search engine snippets as the corpus for answering questions. In particular, three issues are analyzed: (i) the appropriateness of query-focused (QF) summarization rather than generic summarization for the QA task, (ii) the suitable length comparing short and long summaries, and (iii) the benefits of using TS instead of snippets for finding the answers, tested within two semantic QA approaches (named entities and semantic roles). The results obtained show that QF summarization is better than generic (58% improvement), short summaries are better than long (6.3% improvement), and the use of TS within semantic QA improves the performance for both named-entity-based (10%) and, especially, semantic-role-based QA (47.5%). C 2011 Wiley Periodicals, Inc.

show abstract

“…Furthermore, previous research (Mittal et al 1999) has shown that the average length of complex noun-phrases in summary sentences was more than twice as long than those in non-summary sentences. In addition, Lloret and Palomar (2009) carried out a preliminary study of the percentage of noun-phrases contained in both source documents and model summaries of a corpus of a newswire and another one of fairy tales. This analysis showed that words belonging to noun-phrases were predominant over other types of words in the documents as well as in the summaries, representing on average more than 70% of all content words (i.e.…”

Section: Relevance Detectionmentioning

confidence: 99%

COMPENDIUM: a text summarisation tool for generating summaries of multiple purposes, domains, and genres

Lloret¹,

Palomar²

2012

Nat. Lang. Eng.

Self Cite

View full text Add to dashboard Cite

In this paper, we present a Text Summarisation tool, compendium, capable of generating the most common types of summaries. Regarding the input, single-and multi-document summaries can be produced; as the output, the summaries can be extractive or abstractiveoriented; and finally, concerning their purpose, the summaries can be generic, query-focused, or sentiment-based. The proposed architecture for compendium is divided in various stages, making a distinction between core and additional stages. The former constitute the backbone of the tool and are common for the generation of any type of summary, whereas the latter are used for enhancing the capabilities of the tool. The main contributions of compendium with respect to the state-of-the-art summarisation systems are that (i) it specifically deals with the problem of redundancy, by means of textual entailment; (ii) it combines statistical and cognitive-based techniques for determining relevant content; and (iii) it proposes an abstractive-oriented approach for facing the challenge of abstractive summarisation. The evaluation performed in different domains and textual genres, comprising traditional texts, as well as texts extracted from the Web 2.0, shows that compendium is very competitive and appropriate to be used as a tool for generating summaries.

show abstract

A Gradual Combination of Features for Building Automatic Summarisation Systems

Cited by 27 publications

References 9 publications

A Survey of Relevant Text Content Summarization Techniques

A Survey of Relevant Text Content Summarization Techniques

Text summarization contribution to semantic question answering: New approaches for finding answers on the web

COMPENDIUM: a text summarisation tool for generating summaries of multiple purposes, domains, and genres

Contact Info

Product

Resources

About