SUMMA. A Robust and Adaptable Summarization Tool
نویسنده
چکیده
Over the last few years there has been substantial research on text summarization, but comparatively little research has been carried out on adaptable components that allow rapid development and evaluation of summarization solutions. This paper presents a set of adaptable summarization components together with well-established evaluation tools, all within the GATE paradigm. The toolkit includes resources for the computation of summarization features which are combined in order to provide functionalities for single-document, multi-document, querybased, and multi/cross-lingual summarization. The summarization tools have been successfully used in a number of applications including a fully-fledged information access system. RÉSUMÉ. Au cours des dernières années il y a eu un nombre important de recherches au sujet du résumé automatique. Toutefois, il y a eu comparativement peu de recherche au sujet des ressources computationnelles et composantes qui peuvent être adaptées facilement pour le développement et l’évaluation des systèmes de résumé automatique. Ici on présente un ensemble de ressources spécifiquement développées pour le résumé automatique qui se basent sur la plateforme GATE. Les composantes sont utilisées pour calculer des traits indiquant la pertinence des phrases. Ces composantes sont combinées pour produire différents types de systèmes de résumé tels que résumé de document simple, résumé de document multiple, et résumé basé sur des topiques. Les ressources et algorithmes implémentés ont été utilisés pour développer plusieurs applications pour l’accès à l’information dans des systèmes d’information.
منابع مشابه
Creating Summarization Systems with SUMMA
Automatic text summarization, the reduction of a text to its essential content is fundamental for an on-line information society. Although many summarization algorithms exist, there are few tools or infrastructures providing capabilities for developing summarization applications. This paper presents a new version of SUMMA, a text summarization toolkit for the development of adaptive summarizati...
متن کاملHierarchical Summarization: Scaling Up Multi-Document Summarization
Multi-document summarization (MDS) systems have been designed for short, unstructured summaries of 10-15 documents, and are inadequate for larger document collections. We propose a new approach to scaling up summarization called hierarchical summarization, and present the first implemented system, SUMMA. SUMMA produces a hierarchy of relatively short summaries, in which the top level provides a...
متن کاملUsing SUMMA for Language Independent Summarization at TAC 2011
The paper describes a language independent multi-document centroid-based summarization system. The system has been evaluated in the 2011 TAC Multilingual Summarization pilot task where summaries were automatically produced for document clusters in Arabic, English, French and Hindi. The system had a reasonable performance in content selection for languages such as Arabic and Hindi and medium per...
متن کاملELES: Combining Entity Linking and Entity Summarization
The automatic annotation of textual content with entities from a knowledge base is a well established field. Applications, such as DBpedia Spotlight and GATE enable to identify and disambiguate entities of text at high levels of accuracy. The output of such systems can be used in many different ways. One way is to show knowledge panels which provide a fact-based summary of an entity and provide...
متن کاملEXTRACTION-BASED TEXT SUMMARIZATION USING FUZZY ANALYSIS
Due to the explosive growth of the world-wide web, automatictext summarization has become an essential tool for web users. In this paperwe present a novel approach for creating text summaries. Using fuzzy logicand word-net, our model extracts the most relevant sentences from an originaldocument. The approach utilizes fuzzy measures and inference on theextracted textual information from the docu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- TAL
دوره 49 شماره
صفحات -
تاریخ انتشار 2008