50 Hits in 3.7 sec

A summarization system for Chinese news from multiple sources

Hsin-Hsi Chen, June-Jei Kuo, Sheng-Jie Huang, Chuan-Jie Lin, Hung-Chia Wung
2003 Journal of the American Society for Information Science and Technology  
For the evaluation, a question answering system (QA system) is proposed to substitute the human assessors.  ...  It employs not only named entities and other signatures to cluster news from different sources, but also employs punctuation marks, linking elements, and topic chains to identify the meaningful units (  ...  An Evaluation Model Using Question Answering System Model Using Question Answering System To improve the QA task and verify the experimental results, a Question Answering system is used to substitute  ... 
doi:10.1002/asi.10315 fatcat:zdnrhmkax5cnxk2bo6pzp3u2zu

IIIT Hyderabad at TAC 2008

Vasudeva Varma, Prasad Pingali, Rahul Katragadda, Sai Krishna, Surya Ganesh, Kiran Sarvabhotla, Harish Garapati, Hareen Gopisetty, Vijay Bharath Reddy, Kranthi Reddy B, Praveen Bysani, Rohit G. Bharadwaj
2008 Text Analysis Conference  
QA and Summarization Track, we leveraged on our existing Summarization engine and used a classification based approach to both finding opinionated sentences and also the polarity of the opinions.  ...  In the Opinion QA and Summarization Track for the rigid list questions, we have added some additional features to handle opinion expressed in the question. and for the squishy list questions in Opinion  ...  Answering Squishy list in TAC08 QA track is some what similar to descriptive type of question answering, So we have decided to use the summarization system we designed for "DUC 07 multidocument summarization  ... 
dblp:conf/tac/VarmaPKKGSGGRBB08 fatcat:qvzb4p6qhvbwphqvv5wdib4smy

ICTCAS's ICTGrasper at TAC 2008: Summarizing Dynamic Information with Signature Terms Based Content Filtering

Jin Zhang, Xueqi Cheng, Hongbo Xu, Xiaolei Wang, Yiling Zeng
2008 Text Analysis Conference  
This paper presents our new, topic-oriented multi-document summarization system used in TAC 2008.  ...  To deal with the problem of summarizing changes of the dynamic information with time going, we propose a novel summarization method with signature terms based content filtering.  ...  documents to answer a question or a set of questions as posed in a DUC topic.  ... 
dblp:conf/tac/ZhangCXWZ08 fatcat:xj4l7j4qqvht5f5h5ylphp3zou

Answering Questions from Multiple Documents - the Role of Multi-Document Summarization

Pinaki Bhaskar
2013 Recent Advances in Natural Language Processing  
Now, document graph-based query focused multidocument summarizer is used where question words are used as query.  ...  Ongoing research work on Question Answering using multi-document summarization has been described. It has two main sub modules, document retrieval and Multi-document Summarization.  ...  NeATS (Lin and Hovy, 2002) selects important content using sentence position, term frequency, topic signature and term clustering.  ... 
dblp:conf/ranlp/Bhaskar13 fatcat:mjw255widrfkxct2diozlxro2y

Text Summarization Techniques: A Brief Survey [article]

Mehdi Allahyari, Seyedamin Pouriyeh, Mehdi Assefi, Saeid Safaei, Elizabeth D. Trippe, Juan B. Gutierrez, Krys Kochut
2017 arXiv   pre-print
This volume of text is an invaluable source of information and knowledge which needs to be effectively summarized to be useful.  ...  In this review, the main approaches to automatic text summarization are described.  ...  Utilizing topic signature words as topic representation was very effective and increased the accuracy of multidocument summarization in the news domain [29] .  ... 
arXiv:1707.02268v3 fatcat:mq77jgh56ra57jjhf4s5lqq7ie

Tweet Contextualization (Answering Tweet Question) - the Role of Multi-document Summarization

Pinaki Bhaskar, Somnath Banerjee, Sivaji Bandyopadhyay
2013 Conference and Labs of the Evaluation Forum  
The Offline multi-document summarization system is based on document graph, clustering and sentence compression. In the Focused IR system, Wikipedia documents are indexed using Lucene with NE field.  ...  In our system there are three major sub-systems; i) Offline multi-document summarization, ii) Focused IR and iii) online multi-document Summarization.  ...  Starting in 1999, the Text Retrieval Conference (TREC) 1 has sponsored a question-answering track, which evaluates systems that answer factual questions by consulting the documents of the TREC corpus.  ... 
dblp:conf/clef/BhaskarBB13 fatcat:bdhrsixvhjft3jcitffjjad2f4

Answering complex questions with random walk models

Sanda Harabagiu, Finley Lacatusu, Andrew Hickl
2006 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06  
answer by a Multi-Document Summarization (MDS) system.  ...  In our evaluations, we show that access to the decompositions generated using this method can significantly enhance the relevance and comprehensiveness of summarylength answers to complex questions.  ...  All these answers are considered separate documents, which are used to produce a multidocument summary as the third answer (MDS) (Answer Summary 3 illustrated in Figure 1 ).  ... 
doi:10.1145/1148170.1148211 dblp:conf/sigir/HarabagiuLH06 fatcat:pslb7f75uvgh7oim4fzenhgviq

The challenging task of summary evaluation: an overview

Elena Lloret, Laura Plaza, Ahmet Aker
2017 Language Resources and Evaluation  
Therefore, a clear up-to-date overview of the evolution and progress of summarization evaluation is provided, giving the reader useful insights into the past, present and latest trends in the automatic  ...  To perform an adequate evaluation is of great relevance to ensure that automatic summaries can be useful for the context and/or application they are generated for.  ...  Signature terms (also known as topic signatures) are word vectors related to a particular topic.  ... 
doi:10.1007/s10579-017-9399-2 fatcat:tduxzlv2hfbfvd6evzoxn5xibu

Linguistic challenges in automatic summarization technology

Elke Diedrichsen
2017 Journal of Computer-Assisted Linguistic Research  
Automatic summarization is a field of Natural Language Processing that is increasingly used in industry today.  ...  Summarization technologies are also used for image collection summarization and video summarization, but the scope of this paper will be limited to document summarization.  ...  Furthermore, one distinguishes between single and multi-document summarization. Multidocument summarization is specifically useful for information extraction from the web.  ... 
doi:10.4995/jclr.2017.7787 fatcat:xl2gzccpj5ft7dngtrztrkfrlu

Summarization from medical documents: a survey

Stergos Afantenos, Vangelis Karkaletsis, Panagiotis Stamatopoulos
2005 Artificial Intelligence in Medicine  
Finally, it presents and discusses the summarization techniques used so far in the medical domain, referring to the corresponding systems and their characteristics.  ...  types of summarization techniques.  ...  Irene Doura for checking the use of English.  ... 
doi:10.1016/j.artmed.2004.07.017 pmid:15811783 fatcat:n7u6ji5t2rgkvjktacjf4rdire

Literature Review on Extractive Text Summarization Approaches

Saiyed Saziyabegum, Priti S.
2016 International Journal of Computer Applications  
Therefore research community is developing new approaches to for automatic text summarization. Automatic text summarization system creates summary.  ...  Summary is shorter text that covers important information from original document. Summary can be created using extractive and abstractive methods.  ...  The same problem is with multidocument summarization, because extraction of text is performed on different sources.  ... 
doi:10.5120/ijca2016912574 fatcat:zwxchjs5wve57jrmgd2nkl4jhm

Topic-sensitive multi-document summarization algorithm

Liu Na, Tang Di, Lu Ying, Tang Xiao-Jun, Wang Hai-Wen
2015 Computer Science and Information Systems  
Latent Dirichlet Allocation (LDA) has been used to generate text corpora topics recently. However, not all the estimated topics are of equal importance or correspond to genuine themes of the domain.  ...  Some of the topics can be a collection of irrelevant words or represent insignificant themes. This paper proposed a topic-sensitive algorithm for multi-document summarization.  ...  Each set has between 5 and 15 documents, with an average of 10 documents which are produced using data from the TREC disks used in the question-answering track in TREC-9.  ... 
doi:10.2298/csis140815060n fatcat:qkeaeycbd5cy7mdmiikwmzyd5y

Summary in context

Daniel M. McDonald, Hsinchun Chen
2006 ACM Transactions on Information Systems  
The use of text summaries in information-seeking research has focused on query-based summaries.  ...  Summarizers that focus the summary on a topic or user are "query-based" summaries.  ...  ACKNOWLEDGMENTS We would like to thank Kathy McKeown and Hongyan Jing for allowing us to use their TREC summarization data.  ... 
doi:10.1145/1125857.1125861 fatcat:m5hfl3b6efc2bcum5qj4jtbitq

A Survey of Text Summarization Extractive Techniques

Vishal Gupta, Gurpreet Singh Lehal
2010 Journal of Emerging Technologies in Web Intelligence  
It uses linguistic methods to examine and interpret the text and then to find the new concepts and expressions to best describe it by generating a new shorter text that conveys the most important information  ...  It is very difficult for human beings to manually summarize large documents of text. Text Summarization methods can be classified into extractive and abstractive summarization.  ...  It is an extraction-based multidocument summarization system.  ... 
doi:10.4304/jetwi.2.3.258-268 fatcat:anms2x4aczftdnedejeo2tznwm

Summarizing with Encyclopedic Knowledge

Vivi Nastase, Katja Filippova, David N. Milne
2009 Text Analysis Conference  
This paper presents a topic-driven multidocument summarization approach that relies on linking documents to Wikipedia.  ...  The system is trained and developed using the DUC 2005 and 2006 data. It was tested on the DUC 2007 data before deploying it on the update summarization task of TAC 2009.  ...  Biadsy et al. (2008) develop an unsupervised multidocument extractive summarization system to produce biographies.  ... 
dblp:conf/tac/NastaseFM09 fatcat:qvqxsjo5grfh5ipf22cdrfx4wq
« Previous Showing results 1 — 15 out of 50 results