Résultats de recherche pour « Automatic Document Summarization »

Current research in automatic single-document summarization is dominated by two effective, yet naïve approaches: summarization by sentence extraction and headline generation via bagof-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techniques have been developed to extract appropriate training data for them from existing document/abstract and document/ headline corpora. We believe that future progress in automatic summarization will be driven both by the development of more sophisticated, linguistically informed models, as well as a more effective leveraging of document/abstract corpora. In order to open the doors to simultaneously achieving both of these goals, we have developed techniques for automatically producing word-to-word and phrase-to-phrase alignments between documents and their human-written abstracts. These alignments make explicit the correspondences that exist in such document/abstract pairs and create a potentially rich data source from which complex summarization algorithms may learn. This paper describes experiments we have carried out to analyze the ability of humans to perform such alignments, and based on these analyses, we describe experiments for creating them automatically. Our model for the alignment task is based on an extension of the standard hidden Markov model and learns to create alignments in a completely unsupervised fashion. We describe our model in detail and present experimental results that show that our model is able to learn to reliably identify word- and phrase-level alignments in a corpus of (document, abstract) pairs.

Herkömmliche Suchmaschinen filtern die großen Mengen im Internet verfügbarer Daten durch die Abbildung einer Nutzer-Suchanfrage auf eine potentiell große Menge von Dokumenten. Das Auffinden der gesuchten Informationen innerhalb dieser Dokumente bleibt jedoch Aufgabe des Nutzers. Daher ist die Entwicklung computergestützten Methoden essentiell, welche über herkömmliche, dokumentenzentrische Informationsbeschaffungslösungen hinausgehen, und die den Nutzer bei der Verarbeitung großer Dokumentenmengen und darin enthaltener Informationen unterstützen. Automatisierte Textzusammenfassung ist eine solche Technologie, da Zusammenfassungen konzise die Kernpunkte wesentlich größerer Quelltexte zusammentragen und dabei irrelevante und redundante Informationen herausfiltern. Textzusammenfassungssysteme können also ein mächtiges Werkzeug zur Reduktion der von einem Nutzer zu verarbeitenden Datenmengen darstellen. Im Rahmen dieser Arbeit werden Algorithmen zur personalisierten Zusammenfassung von Kollektionen thematisch aufeinander bezogener Nachrichtenartikel entworfen und evaluiert. Von speziellem Interesse ist hierbei die Identifikation der Unterthemen, die das übergeordnete Hauptthema einer solchen Kollektion strukturieren, da dieses die Bestimmung wesentlicher Inhalte und die Erkennung von Redundanzen erleichtert. Existierende Modellierungsverfahren berücksichtigen nicht in ausreichendem Maße die Mehrdeutigkeit natürlicher Sprache und die Begrenztheit von Satzvokabularen. Die in dieser Arbeit entwickelten Algorithmen hingegen werten Wortkontextinformationen zur Themenerkennung aus, und profitieren von den dadurch gegebenen Zusatzinformationen bei der Erstellung personalisierter Zusammenfassungen. Ausführliche Tests in verschiedenen Szenarien und für unterschiedliche Datensätze zeigen, dass die entwickelten Lösungen Zusammenfassungen von höherer Qualität liefern als existierende Ansätze. Nachrichtenartikel, die über ein bestimmtes Ereignis berichten, sind nicht nur ähnlich in Hinblick auf ihre Unterthemen, sondern enthalten auch oft die gleichen Fakten. Die Erkennung ähnlicher Fakten ist eine wünschenswerte, aber derzeit ungelöste Teilaufgabe von Zusammenfassungssystemen, da eine Bewertung der semantischen Ähnlichkeit von Teilsätzen nicht mit der benötigten Präzision möglich ist. Einen weiteren Schwerpunkt dieser Arbeit bilden daher eine ausführliche Analyse von faktenähnlichen Satzabschnitten in Nachrichtenartikeln und Referenzzusammenfassungen, sowie die Entwicklung eines Algorithmus zur Erkennung ähnlicher Teilsätze.

Document summarization is the process of generating the summary of the documents gathered from the web sources. It reduces the burden of web readers by reducing the necessity of reading the entire document contents by generating the short summary. In our previous research work this is performed by introducing the method namely Noun weight based Automated Multi-Document Summarization method (NW-AMDSM). However the previous research work doesn’t concentrate on the semantic similarity which might reduce the accuracy of the summarization outcome. This is resolved in the proposed research method by introducing the method namely Semantic Similarity based Automatic Document Summarization Method (SS-ADSM). In this research work, multi document grouping is done is based on semantic similarity computation, thus the document with similar contents can be grouped more accurately. Here the semantic similarity computation is performed with the help of word net analyzer. The document grouping is done by introducing the modified FCM clustering algorithm. Finally hybrid neuro fuzzy genetic algorithm is introduced to perform the automatic summarization. The numerical analysis of the proposed research method is conducted in the matlab simulation environment and compared with other research methods in terms various performance metrics. The simulation analysis proved proposed method tends to have better performance in terms of increased accuracy of document summarization outcome.

Actual problem in nowadays is to efficiently process the large amount of data that pass through our mind everyday. The object of study of this paper is automatic summarization algorithms. The main goal is to implement and make comparison of different summarization techniques on corpora of news articles parsed from the web. This research work contains the description of three summarization techniques based on TextRank algorithm: General TextRank, BM25, LongestCommonSubstring. It is specially noted the languages of used corpora: Russian and Kazakh languages. The results of summarization processes and their comparison are provided. It should be emphasized that used algorithms are well-known, but the way of their evaluation on defined corpora is different from those which usually used in summary evaluation. The method of summary evaluation proposed use the special dictionary of extracted key-words on the topic of corpora. As the title implies the article describes applying statistical information. The semantic and syntactic features of text are not examined.

In this paper, we propose a automatic document summarization method based on Principal Component Analysis(PCA) which is one of the multivariate statistical methods. After extracting thematic words using PCA, we select the statements containing the respective extracted thematic words, and make the document summary with them. Experimental results using newspaper articles show that the proposed method is superior to the method using either word frequency or information retrieval thesaurus.

제로 클라이언트 체제는 기업의 문서 중앙화를 위해 제시된 최신의 방법이며, 이를 기업의 현실에 보다 적합하도록 토착화시키는 작업은 필수적이다. 본 연구는 제로 클라이언트 체제의 잘 알려진 보안 및 프라이버시 상의 문제점을 제외한, 사용 상의 문제점을 보완하고자 고안되었다. 즉, 작업자가 작업한 문서를 기업 클라우드 스토리지에 저장하고자 저장 카테고리를 검색하는 과정의 부담과 정확성을 향상시키기 위하여, 작업 문서의 주제어를 자동으로 파악하고, 이를 바탕으로 해당 문서가 저장되어야 하는 카테고리를 자동으로 검색하여 작업자의 확인을 통해 자동 저장되도록 하는, 지능적 아카이빙 방식을 제시한다. 본 연구에서 제시하는 주제어 자동 파악 및 자동 아카이빙을 위한 방법론과 프로토타입 시스템은 기업 환경에 적용이 가능할 정도로 정확성과 확장성을 갖추고 있다. Zero client-based cloud storage technology is gaining much interest as a tool to centralized management of organizational documents nowadays. Besides the well-known cloud storage's defects such as security and privacy protection, users of the zero client-based cloud storage point out the difficulty in browsing and selecting the storage category because of its diversity and complexity. To resolve this problem, this study proposes a method of intelligent document archiving by applying an algorithm-based automatic topic identification technology. Without user's direct definition of category to store the working document, the proposed methodology and prototype enable the working documents to be automatically archived into the predefined categories according to the extracted topic. Based on the proposed ideas, more effective and efficient centralized management of electronic documents can be achieved.

The increasing availability of online information has triggered an intensive research in the area of automatic text summarization within the Natural Language Processing (NLP). Text summarization reduces the text by removing the less useful information which helps the reader to find the required information quickly. There are many kinds of algorithms that can be used to summarize the text. One of them is TF-IDF (TermFrequency-Inverse Document Frequency). This research aimed to produce an automatic text summarizer implemented with TF-IDF algorithm and to compare it with other various online source of automatic text summarizer. To evaluate the summary produced from each summarizer, The F-Measure as the standard comparison value had been used. The result of this research produces 67% of accuracy with three data samples which are higher compared to the other online summarizers.

Since 2001, the Document Understanding Conferences have been the forum for researchers in automatic text summarization to compare methods and results on common test sets. Over the years, several types of summarization tasks have been addressed--single document summarization, multi-document summarization, summarization focused by question, and headline generation. This paper is an overview of the achieved results in the different types of summarization tasks. We compare both the broader classes of baselines, systems and humans, as well as individual pairs of summarizers (both human and automatic). An analysis of variance model is fitted, with summarizer and input set as independent variables, and the coverage score as the dependent variable, and simulation-based multiple comparisons were performed. The results document the progress in the field as a whole, rather then focusing on a single system, and thus can serve as a future reference on the work done up to date, as well as a starting point in the formulation of future tasks. Results also indicate that most progress in the field has been achieved in generic multi-document summarization and that the most challenging task is that of producing a focused summary in answer to a question/topic.

In today world, there is a huge amount of information is growing every day on the internet and from many other sources and there is lots of textual information in it. To find out the relevant information from this large amount of data, we need an automatic mechanism that will extract the useful data. Such automatic systems are automatic summarization systems. They categorized into extractive and abstractive summarization system. Extractive summarization systems select the important sentences directly from the large document and put into summary whereas abstractive methods understand semantic meaning of the document by linguistic method to interpret and examine the text. In the purposed method, a statistical approach is used where multiple criterions or features are discussed to calculate the score for every sentence and then SIR (Susceptible Infected Recovered) model is used to compute the dynamic weight for every feature. After dynamic weight computation, weighted TOPSIS (The Technique for Order of Preference by Similarity to Ideal Solution) is used for multi-criterion analysis and aggregation. This method is fully implemented and integrated for automated textual document summarization system.