Filters








949 Hits in 4.4 sec

AUSUM

Senthil Mani, Rose Catherine, Vibha Singhal Sinha, Avinava Dubey
2012 Proceedings of the ACM SIGSOFT 20th International Symposium on the Foundations of Software Engineering - FSE '12  
Automatic summarization of bug reports is one way to reduce the amount of data a developer might need to go through. Prior work has presented learning based approaches for bug summarization.  ...  These derail the unsupervised approaches, which are optimized to work on more well-formed documents.  ...  Acknowledgment We would like to thank Ananthkumar Peddi and Randeep Ghosh of IBM DB2 team for manually summarizing the DB2 bug reports. Thanks are also due to Sarah Rastkar and Gail C.  ... 
doi:10.1145/2393596.2393607 dblp:conf/sigsoft/ManiCSD12 fatcat:a2njorsi3bbqdjkchnxsflkc7y

An Unsupervised Masking Objective for Abstractive Multi-Document News Summarization [article]

Nikolai Vogler, Songlin Li, Yujie Xu, Yujian Mi, Taylor Berg-Kirkpatrick
2022 arXiv   pre-print
We show that a simple unsupervised masking objective can approach near supervised performance on abstractive multi-document news summarization.  ...  Our method trains a state-of-the-art neural summarization model to predict the masked out source document with highest lexical centrality relative to the multi-document group.  ...  Instead of computing centroid-based score functions to produce an output, in our approach we will use them to select a masked document candidate as an unsupervised objective for training a neural abstractive  ... 
arXiv:2201.02321v1 fatcat:ecvuwl77hvdqtlstqzo42ntsmi

LexRank: Graph-based Lexical Centrality as Salience in Text Summarization

G. Erkan, D. R. Radev
2004 The Journal of Artificial Intelligence Research  
We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences.  ...  We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS).  ...  458 LexRank: Graph-based Lexical Centrality as Salience in Text Summarization In Section 2, we present centroid-based summarization, a well-known method for judging sentence centrality.  ... 
doi:10.1613/jair.1523 fatcat:6f5nol2haba7zcphoxjz2qslwe

Extractive Text Summarization Using Recent Approaches: A Survey

Avaneesh Kumar Yadav, Ashish Kumar Maurya, Ranvijay, Rama Shankar Yadav
2021 Ingénierie des Systèmes d'Information  
Many authors proposed various techniques for both types of text summarization. This paper presents a survey of extractive text summarization on graphical-based techniques.  ...  Text summarization is a process that generates a brief version of the document in the form of a meaningful summary.  ...  ACKNOWLEDGMENT We thank innominate reviewers for helpful advices. This research was partially supported by Ministry of Human Resource Development (MHRD), Government of India (GoI).  ... 
doi:10.18280/isi.260112 fatcat:zwo7neckujanliou7arlaiccj4

A new graph based text segmentation using Wikipedia for automatic text summarization

Mohsen Pourvali, Ph.D. Mohammad
2012 International Journal of Advanced Computer Science and Applications  
Document summarization is a process of automatically creating a compressed version of a given document that provides useful information to users, and multi-document summarization is to produce a summary  ...  According to the input text, in this paper we use the knowledge base of Wikipedia and the words of the main text to create independent graphs. We will then determine the important of graphs.  ...  Most commonly, such ranking approaches use some kind of similarity or centrality metric to rank sentences for inclusion in the summarysee, for example [1] .The centroid-based method [3] is one of the  ... 
doi:10.14569/ijacsa.2012.030105 fatcat:ki4mfbykgbbmhjdvfx6mha43xu

Using Wikipedia Anchor Text and Weighted Clustering Coefficient to Enhance the Traditional Multi-document Summarization [chapter]

Niraj Kumar, Kannan Srinathan, Vasudeva Varma
2012 Lecture Notes in Computer Science  
Similar to the traditional approach, we consider the task of summarization as selection of top ranked sentences from ranked sentenceclusters.  ...  We use page rank score of words for calculation of weighted clustering coefficient.  ...  Related Work A lot of methods have been proposed for multi-document summarization.  ... 
doi:10.1007/978-3-642-28601-8_33 fatcat:bgkoszveuzfblfdw5jrhmdreju

Explorations in Automatic Book Summarization

Rada Mihalcea, Hakan Ceylan
2007 Conference on Empirical Methods in Natural Language Processing  
We introduce a new data set specifically designed for the evaluation of systems for book summarization, and describe summarization techniques that explicitly account for the length of the documents.  ...  on the summarization of very long documents.  ...  for suggesting Cliff's Notes as a source of book summaries.  ... 
dblp:conf/emnlp/MihalceaC07 fatcat:sxaboeggkjhrbab6c7h2ffcdkm

Sentence Embedding Based Semantic Clustering Approach for Discussion Thread Summarization

Atif Khan, Qaiser Shah, M. Irfan Uddin, Fasee Ullah, Abdullah Alharbi, Hashem Alyami, Muhammad Adnan Gul
2020 Complexity  
With this motivation behind, this study has proposed a sentence embedding based clustering approach for discussion thread summarization.  ...  Empirical results confirm that the proposed sentence based clustering approach performed superior in comparison to other summarization methods in the context of mean precision, recall, and F-measure.  ...  [40] employed graph-based PR algorithm for summarization of Vietnamese documents.  ... 
doi:10.1155/2020/4750871 fatcat:rrvrfjq5qfggrbwyp5cb3jmrzm

Automated Text Summarization Base on Lexicales Chain and graph Using of WordNet and Wikipedia Knowledge Base [article]

Mohsen Pourvali, Mohammad Saniee Abadeh
2012 arXiv   pre-print
Document summarization is a process of automatically creating a compressed version of a given document that provides useful information to users, and multi-document summarization is to produce a summary  ...  base on the knowledge base.  ...  Most commonly, such ranking approaches use some kind of similarity or centrality metric to rank sentences for inclusion in the summary -see, for example, [1] .The centroid-based method [3] is one of  ... 
arXiv:1203.3586v1 fatcat:sekki4lqgjf3ze3w3grhi3jwxe

Self-Supervised and Controlled Multi-Document Opinion Summarization [article]

Hady Elsahar, Maximin Coavoux, Matthias Gallé, Jos Rozen
2020 arXiv   pre-print
We propose a self-supervised setup that considers an individual document as a target summary for a set of similar documents.  ...  Our benchmarks on two datasets against graph-based and recent neural abstractive unsupervised models show that our proposed method generates summaries with a superior quality and relevance.This is confirmed  ...  Revisiting the centroid-based method: A strong baseline for multi-document summarization.  ... 
arXiv:2004.14754v2 fatcat:a7dh2rdzpnbrxkjf3ghv3z7hi4

Context-Enhanced Personalized Social Summarization

Po Hu, Dong-Hong Ji, Chong Teng, Yujing Guo
2012 International Conference on Computational Linguistics  
This paper proposes a novel unsupervised approach by making use of enhanced social context to aid personalized summary generation.  ...  Most existing summarization systems generate a uniform version of summary for different users no matter who is reading or generate personalized summaries employing only the local information in the document  ...  LexRank: It first constructs a sentence affinity graph based on the Cosine similarity between sentences in a document, and then extracts a few informative sentences based on eigenvector centrality (Erkan  ... 
dblp:conf/coling/HuJTG12 fatcat:n3722fgklbdxdf7bgexupnskbq

A Comprehensive Review of Arabic Text summarization

Asmaa Elsaid, Ammar Mohammed, Lamiaa Fattouh, Mohamed Sakre
2022 IEEE Access  
This paper reviews text summarization approaches and recent deep learning models for this approach.  ...  Although Arabic is a widely spoken language that is frequently used for content sharing on the web, Arabic text summarization of Arabic content is limited and still immature because of several problems  ...  Two ways of summarizing are presented: a graph-based approach and a query-based approach. A query-based strategy: They discovered that the models had improved. Both summarizing approaches are used.  ... 
doi:10.1109/access.2022.3163292 fatcat:spdw4rrvmfgm3anlujx3ndvg2y

From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information [article]

Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, Rui Yan
2020 arXiv   pre-print
Instead, there is much manifold information to be summarized, such as the summary for a web page based on a query in the search engine, extreme long document (e.g., academic paper), dialog history and  ...  Text summarization is the research area aiming at creating a short and condensed version of the original document, which conveys the main idea of the document in a few words.  ...  Acknowledgements We would like to thank the anonymous reviewers for their constructive comments.  ... 
arXiv:2005.04684v1 fatcat:35ub2qoaezdq7fw7ptbvrbj37i

A Process to Support Analysts in Exploring and Selecting Content from Online Forums

Darlinton Carvalho, Ricardo Marcacini, Carlos Lucena, Solange Rezende
2014 Social Networking  
This process is based on unsupervised machine learning techniques like hierarchical clustering and term co-occurrence network.  ...  A tool that helps to apply the proposed process was created to provide consolidated and structured results. This includes measurements and a content exploration interface.  ...  Acknowledgements The authors would like to thank Rodrigo Pazzini for the help with his expert social media skills.  ... 
doi:10.4236/sn.2014.32011 fatcat:q37ibonpkfaejhslopual3iuwu

Incorporating Extra Knowledge to Enhance Word Embedding

Arpita Roy, Shimei Pan
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
important for different NLP applications.  ...  In this survey, we summarize the recent advances in incorporating extra knowledge to enhance word embedding.  ...  Acknowledgments We would like to thank the anonymous reviewers for their constructive comments.  ... 
doi:10.24963/ijcai.2020/676 dblp:conf/ijcai/GaoCR0020 fatcat:n3hj4lad2vcphpmzdnwgflp7x4
« Previous Showing results 1 — 15 out of 949 results