Filters








36,539 Hits in 7.6 sec

Pasokh: A standard corpus for the evaluation of Persian text summarizers

Behdad Behmadi Moghaddas, Mohsen Kahani, Seyyed Ahmad Toosi, Asef Pourmasoumi, Ahmad Estiri
2013 ICCKE 2013  
Keywords-computational processing of Persian;single document automatic summarization;multi-document automatic summarization; evaluation of automatic summarization;evaluation corpus I.  ...  The evaluation is done by comparing the machine summaries against a standard reference corpus containing a reasonably large number of text sources and the summaries that human beings have made out of them  ...  ACKNOWLEDGMENT The authors are grateful for the aid they received from Dr. Nader Jahangiri and the students of the Department of Linguistics at Ferdowsi University of Mashhad.  ... 
doi:10.1109/iccke.2013.6682873 fatcat:ccgbzr5j2vb27kreywpltoj2fm

Text Summarization Challenge: An Evaluation Program for Text Summarization [chapter]

Hidetsugu Nanba, Tsutomu Hirao, Takahiro Fukushima, Manabu Okumura
2020 Evaluating Information Retrieval and Access Tasks  
The purpose of the workshop was to facilitate collecting and sharing text data for summarization by researchers in the field and to clarify the issues of evaluation measures for summarization of Japanese  ...  In this chapter, we describe our TSC series, the data used, and the evaluation methods for each task, and the features of TSC evaluation. 1 Many survey papers are now available on text summarization, e  ...  In contrast, in multiple documents with multiple sources, there are many sentences that convey the same content with different words and phrases, or even with identical sentences.  ... 
doi:10.1007/978-981-15-5554-1_3 fatcat:q4rvb5jklzc7jivoazy2p2yqam

A Novel Real-Time Speech Summarizer System for the Learning of Sustainability

Hsiu-Wen Wang, Ding-Yuan Cheng, Chi-Hua Chen, Yu-Rou Wu, Chi-Chun Lo, Hui-Fei Lin
2015 Sustainability  
As the number of speech and video documents increases on the Internet and portable devices proliferate, speech summarization becomes increasingly essential.  ...  The features used in previous research were analyzed and suitable features were selected following experimentation; subsequently, a three-phase real-time speech summarizer for the learning of sustainability  ...  Required research background and relevant technology for this study are (1) corpus-based text summarization approaches; (2) multiple-document summarization; (3) evaluation of automatic summarization; and  ... 
doi:10.3390/su7043885 fatcat:f4b6xft33jbbbcl25fmo5hzteu

Cross-lingual training of summarization systems using annotated corpora in a foreign language

Marina Litvak, Mark Last
2012 Information retrieval (Boston)  
of Konstanz for the technical support in evaluation experiments.  ...  Also, we would like to thank Michael Orlov and Menahem Friedman for consulting on genetic algorithms.  ...  To choose the best summary, multiple candidates should be generated and evaluated for each document (or document cluster).  ... 
doi:10.1007/s10791-012-9210-3 fatcat:jmen6kykybh4fga3wvbubrlyem

Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization [article]

Taehee Jung, Dongyeop Kang, Lucas Mentch, Eduard Hovy
2019 arXiv   pre-print
We find that while position exhibits substantial bias in news articles, this is not the case, for example, with academic papers and meeting minutes.  ...  Despite the recent developments on neural summarization systems, the underlying logic behind the improvements from the systems and its corpus-dependency remains largely unexplored.  ...  We thank Rada Mihalcea for sharing the book summarization dataset. We also thank Diane J. Litman, Taylor Berg-Kirkpatrick, Hiroaki Hayashi, and anonymous reviewers for their helpful comments.  ... 
arXiv:1908.11723v1 fatcat:ph6qsplbhbhzjo5utwxkrontp4

Live Blog Corpus for Summarization [article]

Avinesh P.V.S., Maxime Peyrard, Christian M. Meyer
2018 arXiv   pre-print
In an empirical evaluation using well-known state-of-the-art summarization systems, we show that live blogs corpus poses new challenges in the field of summarization.  ...  We make our tools publicly available to reconstruct the corpus to encourage the research community and replicate our results.  ...  We also acknowledge the useful comments and suggestions of the anonymous reviewers.  ... 
arXiv:1802.09884v1 fatcat:e44vgimfwjgjxp3mgcpbe2qgya

Text summarization in the biomedical domain: A systematic review of recent research

Rashmi Mishra, Jiantao Bian, Marcelo Fiszman, Charlene R. Weir, Siddhartha Jonnalagadda, Javed Mostafa, Guilherme Del Fiol
2014 Journal of Biomedical Informatics  
Text summarization reduces information as an attempt to enable users to find and understand relevant source texts more quickly and effortlessly.  ...  The study identified research gaps and provides recommendations for guiding future research on biomedical text summarization.  ...  Acknowledgments The authors would like to acknowledge Alice Weber for providing insights on the search strategy of this systematic review.  ... 
doi:10.1016/j.jbi.2014.06.009 pmid:25016293 pmcid:PMC4261035 fatcat:jdsabkdlhneldlzelmbdqp3bci

A Novel Framework for Multi-Document Temporal Summarization (MDTS)

Kishore Kumar Mamidala, Suresh Kumar Sanampudi
2021 Emerging Science Journal  
Experiments are conducted on DUC 2006 and DUC 2007 data set that was released for multi-document summarization task.  ...  The extracted summaries are evaluated using ROUGE to determine precision, recall and F measure of generated summaries.  ...  For example, in online news articles, the same topic is published with different views. Summarizing the information from these multiple sources may contain the redundant data into summary.  ... 
doi:10.28991/esj-2021-01268 fatcat:uyj7gz437nc4dknti2w23n3wwa

Cut and Paste Based Text Summarization

Hongyan Jing, Kathleen R. McKeown
2000 Applied Natural Language Processing Conference  
Our work includes a statistically based sentence decomposition program that identifies where the phrases of a summary originate in the original document, producing an aligned corpus of summaries and articles  ...  We present a cut and paste based text summarizer, which uses operations derived from an analysis of human written abstracts.  ...  Acknowledgment We thank IBM for licensing us the ESG parser and the MITRE corporation for licensing us the coreference resolution system.  ... 
dblp:conf/anlp/JingM00 fatcat:5yqj3hxfdjgp3kyma27qrqflsq

Exploring content selection strategies for Multilingual Multi-Document Summarization based on the Universal Network Language (UNL)

Matheus Rigobelo Chaud, Ariani Di Felippo
2017 Revista de Estudos da Linguagem  
; multilingual corpus; multi-document summarization.  ...  We used a bilingual corpus (Brazilian Portuguese-English) encoded in UNL (Universal Network Language) with source and summary sentences aligned based on content overlap.  ...  Acknowledgements The authors thank Coordination for the Improvement of Higher Education Personnel CAPES, CNPq, and State of São Paulo Research Foundation (FAPESP) for the financial support.  ... 
doi:10.17851/2237-2083.26.1.45-71 fatcat:zdfws25qbjg3hhqbslru45c7ki

Introduction to the Special Issue on Summarization

Dragomir R. Radev, Eduard Hovy, Kathleen McKeown
2002 Computational Linguistics  
Barzilay and Elhadad present an evaluation of the approach for summarization with both scientific documents and university textbooks.  ...  The three major problems introduced by having to handle multiple input documents are (1) recognizing and coping with redundancy, (2) identifying important differences among documents, and (3) ensuring  ... 
doi:10.1162/089120102762671927 fatcat:suc42urx2zerdik3q2grlpid3u

Bridging the gap between extractive and abstractive summaries: Creation and evaluation of coherent extracts from heterogeneous sources

Darina Benikova, Margot Mieskes, Christian M. Meyer, Iryna Gurevych
2016 International Conference on Computational Linguistics  
We use a corpus of heterogeneous documents to address the issue that information seekers usually face -a variety of different types of information sources.  ...  Our corpus is available to the research community for further development.  ...  We would like to thank our annotators for their valuable contribution.  ... 
dblp:conf/coling/BenikovaMMG16 fatcat:er664p2ovzfztiii7odl6mllgq

Topic Modeling Based Extractive Text Summarization

2020 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
All extractive sub-summaries are later combined to generate a summary for any given source document. We utilize the lesser used and challenging WikiHow dataset in our approach to text summarization.  ...  Text summarization is an approach for identifying important information present within text documents.  ...  Document Summarization The generated topic clusters for a document tend to divide the document into multiple sub-documents.  ... 
doi:10.35940/ijitee.f4611.049620 fatcat:to2izh7xb5aurgkgqhka2qqhku

Multi-Document Summarization Using Cross-Language Texts

Jung-Min Lim, In-Su Kang, Jong-Hyeok Lee
2004 NTCIR Conference on Evaluation of Information Access Technologies  
For summarizing multiple documents translated by a machine translator, we extract important sentences, and remove redundant sentences using an improved term-weighting method.  ...  Without a summarization system in source language, we try to generate a summary in source language, using translated documents by a machine translator and a summarization system in target language.  ...  Acknowledgements This work was supported by the Korea Science and Engineering Foundation (KOSEF), through the Advanced Information Technology Research Center (AITrc).  ... 
dblp:conf/ntcir/LimKL04 fatcat:3cslcbjgovbazc4lqk2cye5e2q

Towards Generating Citation Sentences for Multiple References with Intent Control [article]

Jia-Yan Wu, Alexander Te-Wei Shieh, Shih-Ju Hsu, Yun-Nung Chen
2021 arXiv   pre-print
We first build a novel generation model with the Fusion-in-Decoder approach to cope with multiple long inputs. Second, we incorporate the predicted citation intents into training for intent control.  ...  Current methods in generating citation text were limited to single citation generation using the citing document and a cited document as input.  ...  The source document and one cited document.  ... 
arXiv:2112.01332v2 fatcat:iqwyqtkgybf53nojlzydalvuki
« Previous Showing results 1 — 15 out of 36,539 results