57,469 Hits in 4.9 sec

A Cognitive Interactive Framework for Multi-Document Summarizer [chapter]

Anupam Srivastava, Divij Vaidya, Malay Singh, Pranjal Singh, U. S. Tiwary
2012 Advances in Intelligent Systems and Computing  
Though we have tested the framework for multi-document summarization, we believe that it can be extended to develop interactive applications for other domains and tasks.  ...  To show the utilization of this framework, Iintelli, an agent based application for multiple text document summarization is developed and compared with the MEAD on the Cran Data Set.  ...  Moreover, we have used a new form of information gathering method in the task of multi-document summarization i.e. through interaction with the users.  ... 
doi:10.1007/978-3-642-31603-6_22 fatcat:ye4mikg2xnehfjtzeijnivimry

Topic-Guided Abstractive Multi-Document Summarization [article]

Peng Cui, Le Hu
2021 arXiv   pre-print
A critical point of multi-document summarization (MDS) is to learn the relations among various documents.  ...  Since topic extraction can be viewed as a special type of summarization that "summarizes" texts into a more abstract format, i.e., a topic distribution, we adopt a multi-task learning strategy to jointly  ...  ., 2017; Srivastava and Sutton, 2017) that learns topic distribution of source documents and corpus-level topic representations, and an abstractive summarizer that incorporates latent topics to summary  ... 
arXiv:2110.11207v1 fatcat:wf6vudj6sfgcbkwbaabkccwn6m

Multi-document Summarization via Deep Learning Techniques: A Survey [article]

Congbo Ma, Wei Emma Zhang, Mingyu Guo, Hu Wang, Quan Z. Sheng
2021 arXiv   pre-print
Multi-document summarization (MDS) is an effective tool for information aggregation that generates an informative and concise summary from a cluster of topic-related documents.  ...  Our survey, the first of its kind, systematically overviews the recent deep learning based MDS models.  ...  [56] proposed a Transformer based multi-granularity interaction network MGSum and unified the extractive and abstractive multi-document summarization.  ... 
arXiv:2011.04843v3 fatcat:zfi52xxef5g2tjkaw6hgjpwa5i

Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization

Sangwoo Cho, Logan Lebanoff, Hassan Foroosh, Fei Liu
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Our findings are particularly meaningful for summarizing documents created by multiple authors containing redundant yet lexically diverse expressions. 1  ...  In this paper we seek to strengthen a DPP-based method for extractive multi-document summarization by presenting a novel similarity measure inspired by capsule networks.  ...  Acknowledgments The authors are grateful to the reviewers for their insightful feedback. We would also like to extend our thanks to Boqing Gong, Xiaodan Zhu and Fei Sha for useful discussions.  ... 
doi:10.18653/v1/p19-1098 dblp:conf/acl/ChoLFL19 fatcat:v4q2comewraivnqpytde3hmyze

Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis [article]

Lingwei Wei, Dou Hu, Wei Zhou, Xuehai Tang, Xiaodan Zhang, Xin Wang, Jizhong Han, Songlin Hu
2021 arXiv   pre-print
A Hierarchical Interaction Networks (HIN) is proposed to explore bidirectional interactions between the summary and document at multiple granularities and learn subject-oriented document representations  ...  However, these summarization-based methods did not take full advantage of the summary including ignoring the inherent interactions between the summary and document.  ...  The text summarization task naturally compresses texts for an abstractive summarization from the long document.  ... 
arXiv:2007.08445v3 fatcat:vambia2wnfexrkmchdihyqh4ka

Semi-supervised Abstraction-Augmented String Kernel for Multi-level Bio-Relation Extraction [chapter]

Pavel Kuksa, Yanjun Qi, Bing Bai, Ronan Collobert, Jason Weston, Vladimir Pavlovic, Xia Ning
2010 Lecture Notes in Computer Science  
This Abstraction-augmented String Kernel (ASK) allows for better generalization of patterns learned from annotated data and provides a unified framework for solving bRE with multiple degrees of detail.  ...  Bio-relation extraction (bRE) , an important goal in bio-text mining, involves subtasks identifying relationships between bio-entities in text at multiple levels, e.g., at the article, sentence or relation  ...  -It provides a unified framework for bRE at multiple levels where tasks have small training sets.  ... 
doi:10.1007/978-3-642-15883-4_9 fatcat:n35jjgwqbncj3jhnf6roebh7yy

CERC: an interactive content extraction, recognition, and construction tool for clinical and biomedical text

Eva K Lee, Karan Uppal
2020 BMC Medical Informatics and Decision Making  
A novel sentence-ranking framework multi indicator text summarization, MINTS, is developed for extractive summarization.  ...  In this work, we develop an interactive content extraction, recognition, and construction system (CERC) that combines machine learning and visualization techniques with domain knowledge for highlighting  ...  Acknowledgements The authors thank the Georgia Tech students, Cody Wang for using and incorporating CERC within his research, Lavannya Atri, Rachel Defilipp, Danielle Mattias, Shanice Saunders, Prashant  ... 
doi:10.1186/s12911-020-01330-8 pmid:33323109 fatcat:neac7vl5fncibnx3kxcktyqmba

HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization [article]

Ye Liu, Jian-Guo Zhang, Yao Wan, Congying Xia, Lifang He, Philip S. Yu
2021 arXiv   pre-print
To mitigate these issues, this paper proposes HETFORMER, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization.  ...  Extensive experiments on both single- and multi-document summarization tasks show that HETFORMER achieves state-of-the-art performance in Rouge F1 while using less memory and fewer parameters.  ...  Acknowledgements We would like to thank all the reviewers for their helpful comments. This work is supported by NSF under grants III-1763325, III-1909323, III-2106758, and SaTC-1930941.  ... 
arXiv:2110.06388v2 fatcat:jn3qpnqq7ffvrgjb7nbtu6zusq

Summarization of discussion groups

Robert Farrell, Peter G. Fairweather, Kathleen Snyder
2001 Proceedings of the tenth international conference on Information and knowledge management - CIKM'01  
We have incorporated this algorithm into a Web-based application called IDS (Interactive Discussion Summarizer).  ...  sentences for each ofP postings into a new topic-level synthesized document with P paragraphs of at most M sentences each, in date order.  ...  ALGORITHM We have developed an algorithm we call hierarchical discussion summorizntion that performs sentence extraction and summarization recursively at multiple levels of a discussion hierarchy (see  ... 
doi:10.1145/502585.502678 dblp:conf/cikm/FarrellFS01 fatcat:hnkq3qxgqbglfmyudiaesdy4zu

A Survey on Dialogue Summarization: Recent Advances and New Frontiers [article]

Xiachong Feng, Xiaocheng Feng, Bing Qin
2021 arXiv   pre-print
However, there remains a lack of comprehensive survey for this task. To this end, we take the first step and present a thorough review of this research field.  ...  We hope that this first survey of dialogue summarization can provide the community with a quick access and a general picture to this task and motivate future researches.  ...  Fabbri and Jiaao Chen for sharing their systems' outputs. We would also like to thank Shiyue Zhang for her feedback on email summarization and Libo Qin for his helpful discussion.  ... 
arXiv:2107.03175v1 fatcat:sxvkutab2balvhohaavugiufom

Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks

Aishwarya Jadhav, Vaibhav Rajan
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We present a new neural sequence-tosequence model for extractive summarization called SWAP-NET (Sentences and Words from Alternating Pointer Networks).  ...  SWAP-NET identifies both salient sentences and key words in an input document, and then combines them to form the extractive summary.  ...  The authors thank the ACL reviewers for their valuable comments.  ... 
doi:10.18653/v1/p18-1014 dblp:conf/acl/JadhavR18 fatcat:l3i2eiz7evh5nnwtl72fo7jj34

MDSWriter: Annotation Tool for Creating High-Quality Multi-Document Summarization Corpora

Christian M. Meyer, Darina Benikova, Margot Mieskes, Iryna Gurevych
2016 Proceedings of ACL-2016 System Demonstrations  
In this paper, we present MDSWriter, a novel open-source annotation tool for creating multi-document summarization corpora.  ...  This allows for evaluating the individual components of a complex summarization system and learning from the human writing process.  ...  Redundancy is a key characteristic of multiple documents about a given topic. Automatic summarization methods aim at removing this redundancy.  ... 
doi:10.18653/v1/p16-4017 dblp:conf/acl/MeyerBMG16 fatcat:4io4sys5dbcjhl2gf45ka5x6fm

Design and development of a concept-based multi-document summarization system for research abstracts

Shiyan Ou, Christopher Soo-Guan Khoo, Dion H. Goh
2008 Journal of information science  
Dissertation abstracts in the field of sociology were selected as sample documents for this study.  ...  This paper describes a new concept-based multi-document summarization system that employs discourse parsing, information extraction and information integration.  ...  summarizing documents into single-document abstracts and then combining the single-document abstracts into one multi-document abstract.  ... 
doi:10.1177/0165551507084630 fatcat:oz44rflbcfcc3ihxnmnf3bsao4

PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies [article]

Andy Su, Difei Su, John M.Mulvey, H.Vincent Poor
2021 arXiv   pre-print
We propose a novel reinforcement learning based framework PoBRL for solving multi-document summarization.  ...  Our strategy decouples this multi-objective optimization into different subproblems that can be solved individually by reinforcement learning.  ...  MGSum (ext/abs), an extractive/abstractive summarization method with Multi-Granularity Interaction Network. (Jin et al., 2020) .  ... 
arXiv:2105.08244v1 fatcat:sjzb23nzfve3jkzf4blr5bwhqu

Systematic black-box analysis of collaborative web applications

Marina Billes, Anders Møller, Michael Pradel
2017 SIGPLAN notices  
Existing techniques for analyzing concurrent software do not scale to such complex systems or do not consider multiple interacting clients.  ...  The second phase synthesizes multi-client interactions targeted at triggering misbehavior that may result from the potential conflicts, and reports an inconsistency if the clients do not converge to a  ...  Acknowledgments We thank the anonymous reviewers and our shepherd Stephen Freund for their comments and guidance.  ... 
doi:10.1145/3140587.3062364 fatcat:47zvimkpfjcabnzknetfya4aqe
« Previous Showing results 1 — 15 out of 57,469 results