Natural language processing · 2001
The world is overloaded with information due to the internet revolution. This calls for an efficient and accurate summarization system to extract relevant information. Text summarization system automatically generates a summary of a given document and helps people to take effective decisions in less time. In this book two methods have been proposed for query-focused multi-document summarization that uses k-mean clustering and term-frequency-inverse-sentence-frequency method for sentence weighting to rank the sentences of the document(s) with respect to a given query. The proposed methods find the proximity of documents and query, and later uses this proximity to rank sentences of each document. A comparative study for proposed methods has been done and experimental results shows that both methods are comparable because of a slight difference in performance. DUC 2007 test dataset and ROUGH-1.5.5 summarization evaluation package is used for evaluation purpose.
Cited by 0
Inderjeet Mani · 2001
Cited by 0
Anton Hägerstrand · 2011
This thesis describes the development and deployment of a search based, automatic, multi-document summarizing system, and shows that technologies regularly used in search engines are applicable to the task of automatic summarization. The summarizer works by first indexing a set of documents as well as extracting sentences from them. The summarizer can then summarize document collections, which are dynamically constructed from the documents in the index. This is done as an addition to the Solr search server, which provides an interface to the Lucene index; the summarizer uses Lucene to find sentences which it can use to create summaries. The summarizer uses methods similar to search engines, and enjoys the same benefits in speed that modern search engines provide when summarizing documents.
Cited by 5
German Research Center for Artificial Intelligence · European Language Grid · 2022
DistilBart (sequence-to-sequence Transformers) trained on WikinewsSum. WikinewsSum is a corpus created from Wikinews where the texts to summarize are the texts of the sources of the Wikinews article, and the summary to obtain is the Wikinews article. The service creates a summary from a source text for English, German, and French. Only the first 1024 tokens of the source text are used to create the summary.
Cited by 0Open access
Liang Zhou, Miruna Ticrea, Eduard Hovy · ArXiv.org · 2005
In this paper we describe a biography summarization system using sentence classification and ideas from information retrieval. Although the individual techniques are not new, assembling and applying them to generate multi-document biographies is new. Our system was evaluated in DUC2004. It is among the top performers in task 5-short summaries focused by person questions.
Cited by 52Open access
Kritharakis Emmanouil, Κριθαρακης Εμμανουηλ · Technical University of Crete · 2019
Τα τελευταία χρόνια, έχει παρατηρηθεί έντονο ενδιαφέρον για την αυτόματη περίληψη κειμένων, καθώς υπάρχουν πολλές εφαρμογές που απαιτούν την συμπίεση της μεγάλης ποσότητας πληροφορίας που είναι διαθέσιμη σε μικρές, συνοπτικές περιλήψεις. Σε αυτή την κατεύθυνση, η περίληψη κειμένου με μοντέλα sequence-to-sequence (seq2seq) έχει προσελκύσει το ενδιαφέρον της επιστημονικής κοινότητας. Παρόμοιες αρχιτεκτονικές κωδικοποίησης-αποκωδικοποίησης (encoder-decoder) έχουν επίσης χρησιμοποιηθεί και σε περίληψη πολλαπλών κειμένων. Ωστόσο, η προσαρμογή των μοντέλων seq2seq πάνω σε περιλήψεις πολλαπλών κειμένων δεν είναι πάντα επιτυχής και απαιτεί εξειδικευμένους μηχανισμούς εστίασης προσοχής (attention) για την αποφυγή περιττών νοηματικών επαναλήψεων. Σε αυτή την εργασία, προτείνουμε έναν καινοτόμο μηχανισμό εστίασης προσοχής, ο οποίος βασίζεται πάνω στην ομοιότητα των προτάσεων, προκειμένου να βελτιώσουμε την περίληψη σε πολλαπλά κείμενα. Με τον προτεινόμενο μηχανισμό, το σύστημα λαμβάνει υπ’ όψιν του την σημασιολογική και συντακτική φύση των προτάσεων, κάτι πολύ χρήσιμο σε δεδομένα από πολλαπλά κείμενα. Για να διερευνήσουμε την αποτελεσματικότητα του αλγορίθμου ομοιότητας των προτάσεων, διεξήγαμε δύο ομάδες πειραμάτων. Στην πρώτη, ο προτεινόμενος αλγόριθμος συγκρίνεται με έναν πρόσφατα δημοσιευμένο αλγόριθμο ομοιότητας προτάσεων. Χρησιμοποιώντας ως κριτήριο τον συντελεστή συσχέτισης Pearson και άλλες στατιστικές μετρήσεις παρατηρήσαμε ότι ο αλγόριθμος μας πετυχαίνει καλύτερα αποτελέσματα. Στη δεύτερη οικογένεια πειραμάτων, ο προτεινόμενος αλγόριθμος ενσωματώθηκε ως μηχανισμός εστίασης προσοχής σε μοντέλα seq2seq για την περίληψη πολλαπλών κειμένων. Η αποτίμηση της επίδοσης με αυτοματοποιημένες μετρικές απέδειξε ότι το προτεινόμενο σύστημα υπερβαίνει συστηματικά σε επίδοση άλλες μεθόδους που βρίσκονται στην αιχμή της τεχνολογίας (state-of-the-art) πάνω στις βάσεις δεδομένων πολλαπλών ειδησεογραφικών κειμένων DUC-2004 και TAC-2011.
Cited by 0Open access
Maâli Mnasri · theses.fr (ABES) · 2018
Cette thèse s’intéresse au Résumé Automatique de texte et plus particulièrement au résumémis-à-jour. Cette problématique de recherche vise à produire un résumé différentiel d'un ensemble denouveaux documents par rapport à un ensemble de documents supposés connus. Elle intègre ainsidans la problématique du résumé à la fois la question de la dimension temporelle de l'information etcelle de l’historique de l’utilisateur. Dans ce contexte, le travail présenté s'inscrit dans les approchespar extraction fondées sur une optimisation linéaire en nombres entiers (ILP) et s’articule autour dedeux axes principaux : la détection de la redondance des informations sélectionnées et la maximisationde leur saillance. Pour le premier axe, nous nous sommes plus particulièrement intéressés àl'exploitation des similarités inter-phrastiques pour détecter, par la définition d'une méthode deregroupement sémantique de phrases, les redondances entre les informations des nouveaux documentset celles présentes dans les documents déjà connus. Concernant notre second axe, nous avons étudiél’impact de la prise en compte de la structure discursive des documents, dans le cadre de la Théorie dela Structure Rhétorique (RS), pour favoriser la sélection des informations considérées comme les plusimportantes. L'intérêt des méthodes ainsi définies a été démontré dans le cadre d'évaluations menéessur les données des campagnes TAC et DUC. Enfin, l'intégration de ces critères sémantique etdiscursif au travers d'un mécanisme de fusion tardive a permis de montrer dans le même cadre lacomplémentarité de ces deux axes et le bénéfice de leur combinaison.
Cited by 0Open access
Ruben Wolhandler, Arie Cattan, Ori Ernst et al. · 2022
The task of multi-document summarization (MDS) aims at models that, given multiple documents as input, are able to generate a summary that combines disperse information, originally spread __across__ these documents. Accordingly, it is expected that both reference summaries in MDS datasets, as well as system summaries, would indeed be based on such dispersed information. In this paper, we argue for quantifying and assessing this expectation. To that end, we propose an automated measure for evaluating the degree to which a summary is "disperse", in the sense of the number of source documents needed to cover its content. We apply our measure to empirically analyze several popular MDS datasets, with respect to their reference summaries, as well as the output of state-of-the-art systems. Our results show that certain MDS datasets barely require combining information from multiple documents, where a single document often covers the full summary content. Overall, we advocate using our metric for assessing and improving the degree to which summarization datasets require combining multi-document information, and similarly how summarization models actually meet this challenge.
Cited by 13Open access
Association for Computational Linguistics 2022, Cattan, Arie, Dagan, Ido et al. · Underline Science Inc. · 2022
The task of multi-document summarization (MDS) aims at models that, given multiple documents as input, are able to generate a summary that combines disperse information, originally spread across these documents. Accordingly, it is expected that both reference summaries in MDS datasets, as well as system summaries, would indeed be based on such dispersed information. In this paper, we argue for quantifying and assessing this expectation. To that end, we propose an automated measure for evaluating the degree to which a summary is ``disperse'', in the sense of the number of source documents needed to cover its content. We apply our measure to empirically analyze several popular MDS datasets, with respect to their reference summaries, as well as the output of state-of-the-art systems. Our results show that certain MDS datasets barely require combining information from multiple documents, where a single document often covers the full summary content. Overall, we advocate using our metric for assessing and improving the degree to which summarization datasets require combining multi-document information, and similarly how summarization models actually meet this challenge.
Cited by 0Open access
Bhakti Mehta · International Journal Of Engineering And Computer Science · 2016
Ontology is defined as conceptual representation data and relationships between this data.In this paper, we propose to use this ontology for summarization of multiple documents related to a specific domain. We explore various techniques that can be used for summarization. We then focus upon a particular approach for summarization of documents belonging to a particular domain.The domain that we have considered is disaster management.As an example we will be taking the earthquake that took place in Nepal in April 2015.Using this example we will demonstrate summarization of multiple documents.
Cited by 0
Anton Leuski, Chin-yew Lin, Eduard Hovy · 2003
We describe iNeATS – an interactive multi-document summarization system that integrates a state-of-the-art summarization engine with an advanced user interface. Three main goals of the system are: (1) provide a user with control over the summarization process, (2) support exploration of the document set with the summary as the staring point, and (3) combine text summaries with alternative presentations such as a map-based visualization of documents. 1
Cited by 0
Jianfeng Gao, Chenyan Xiong, Paul N. Bennett et al. · The information retrieval series · 2023
Cited by 1
Luís Marujo, José Portêlo, Ling Wang et al. · arXiv (Cornell University) · 2015
State-of-the-art extractive multi-document summarization systems are usually designed without any concern about privacy issues, meaning that all documents are open to third parties. In this paper we propose a privacy-preserving approach to multi-document summarization. Our approach enables other parties to obtain summaries without learning anything else about the original documents' content. We use a hashing scheme known as Secure Binary Embeddings to convert documents representation containing key phrases and bag-of-words into bit strings, allowing the computation of approximate distances, instead of exact ones. Our experiments indicate that our system yields similar results to its non-private counterpart on standard multi-document evaluation datasets.
Cited by 9Open access
Yogan Jaya Kumar, Naomie Salim · 2012
Abstract: Problem statement: Text summarization can be of different nature ranging from indicative summary that identifies the topics of the document to informative summary which is meant to represent the concise description of the original document, providing an idea of what the whole content of document is all about. Approach: Single document summary seems to capture both the information well but it has not been the case for multi document summary where the overall comprehensive quality in presenting informative summary often lacks. It is found that most of the existing methods tend to focus on sentence scoring and less consideration is given to the contextual information content in multiple documents. Results: In this study, some survey on multi document summarization approaches has been presented. We will direct our focus notably on four well known approaches to multi document summarization namely the feature based method, cluster based method, graph based method and knowledge based method. The general ideas behind these methods have been described. Conclusion: Besides the general idea and concept, we discuss the benefits and limitations concerning these methods. With the aim of enhancing multi document summarization, specifically news documents, a novel type of approach is outlined to be developed in the future, taking into account the generic components of a news story in order to generate a better summary. Key words: Multi document summarization, extractive summarization, news documents, summarization approaches, ontology learning, generic components, novel text summarization approaches
Cited by 0
2008
We describe iNeATS – an interactive multi-document summarization system that integrates a state-of-the-art summarization engine with an advanced user interface. Three main goals of the system are: (1) provide a user with control over the summarization process, (2) support exploration of the document set with the summary as the staring point, and (3) combine text summaries with alternative presentations such as a map-based visualization of documents. 1
Cited by 0
A M. Harabagiu, Steven J. Maiorano · 2002
This paper presents the architecture and the multidocument summarization techniques implemented in the GISTEXTER system. The paper presents an algorithm for producing incremental multi-document summaries if extraction templates of good quality are available. An empirical method of generating ad-hoc templates that can be populated with information extracted from texts by automatically acquired extraction patterns is also presented. The results of GISTEXTER in the DUC-2001 evaluations account for the advantages of using the techniques presented in this paper. 1.
Cited by 0
Anton Leuski Chin-Yew · 2003
We describe iNeATS -- an interactive multi-document summarization system that integrates a state-of-the-art summarization engine with an advanced user interface.
Cited by 0
Ghiyafeh Davoodi, Fatemeh, University of Lethbridge. Faculty of Arts and Science · Open ULeth Scholarship (OPUS) (University of Lethbridge) · 2015
In this thesis, I design a Maximum Coverage problem with KnaPsack constraint (MCKP) based model for extractive multi-document summarization. The model integrates three measures to detect important sentences including Coverage, rewards sentences in regards to their representative level of the whole document, Relevance, focuses to select sentences that related to the given query, and Compression, rewards concise sentences. To generate a summary, I apply an efficient and scalable greedy algorithm. The algorithm has a near optimal solution when its scoring functions are monotone non-decreasing and submodular. I use DUC 2007 dataset to evaluate our proposed method. Investigating the results using ROUGE package shows improvement over two closely related works. The experimental results illustrates that integrating compression in the MCKP-based model, applying semantic similarity measures to detect Relevance measure and also defining all scoring functions as a monotone submodular function result in having a better performance in generating a summary.
Cited by 0
Xin Zheng, Aixin Sun, Jing Li et al. · 2019
Xin Zheng, Aixin Sun, Jing Li, Karthik Muthuswamy. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
Cited by 22Open access
Kumar · Journal of Computer Science · 2011
Problem statement: Text summarization can be of different nature ranging from indicative summary that identifies the topics of the document to informative summary which is meant to represent the concise description of the original document, providing an idea of what the whole content of document is all about. Approach: Single document summary seems to capture both the information well but it has not been the case for multi document summary where the overall comprehensive quality in presenting informative summary often lacks. It is found that most of the existing methods tend to focus on sentence scoring and less consideration is given to the contextual information content in multiple documents. Results: In this study, some survey on multi document summarization approaches has been presented. We will direct our focus notably on four well known approaches to multi document summarization namely the feature based method, cluster based method, graph based method and knowledge based method. The general ideas behind these methods have been described.
Cited by 58Open access