15,833 Hits in 4.1 sec

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.  ...  Research into unsupervised neural abstractive multi-document summarization is scarcer.  ... 
arXiv:2201.02321v1 fatcat:ecvuwl77hvdqtlstqzo42ntsmi

A Systematic Survey on Multi-document Text Summarization

2021 International Journal of Advanced Trends in Computer Science and Engineering  
Text summarization can be classified based on the number of input documents (single document and multi-document summarization) and based on the characteristics of the summary generated (extractive and  ...  Multi-document summarization is an automatic process of creating relevant, informative and concise summary from a cluster of related documents.  ...  Text summarization can be classified based on the number of input Text summarization can be classified based on different documents (single document and multi-document  ... 
doi:10.30534/ijatcse/2021/111062021 fatcat:rs7d7bltbba6nj5ph3tx3hpgwm

Unsupervised Graph-Based Tibetan Multi-Document Summarization

Xiaodong Yan, Yiqin Wang, Wei Song, Xiaobing Zhao, A. Run, Yang Yanxing
2022 Computers Materials & Continua  
In this paper, we propose an unsupervised graph-based Tibetan multi-document summarization method, which divides a large number of Tibetan news documents into topics and extracts the summarization of each  ...  Then model sentence clusters into graphs, finally remeasure sentence nodes based on the topic semantic information and the impact of topic features on sentences, higher topic relevance summary is extracted  ...  We propose an unsupervised Tibetan multi-document summarization method based on graph model.  ... 
doi:10.32604/cmc.2022.027301 fatcat:fqxgkck3jnebbgxt7xi6qvkq7e

SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization [article]

Yang Gao, Wei Zhao, Steffen Eger
2020 arXiv   pre-print
We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.).  ...  Furthermore, we use SUPERT as rewards to guide a neural-based reinforcement learning summarizer, yielding favorable performance compared to the state-of-the-art unsupervised summarizers.  ...  Guiding Reinforcement Learning We explore the use of different rewards to guide Neural Temporal Difference (NTD), a RL-based multi-document summarizer (Gao et al., 2019a) .  ... 
arXiv:2005.03724v1 fatcat:eu3l5nvln5f7dlp2pnx6ldg5sy

Unsupervised Abstractive Summarization of Bengali Text Documents [article]

Radia Rayan Chowdhury, Mir Tafseer Nayeem, Tahsin Tasnim Mim, Md. Saifur Rahman Chowdhury, Taufiqul Jannat
2021 arXiv   pre-print
To overcome this problem, we propose a graph-based unsupervised abstractive summarization system in the single-document setting for Bengali text documents, which requires only a Part-Of-Speech (POS) tagger  ...  Abstractive summarization systems generally rely on large collections of document-summary pairs.  ...  A cluster of sentences uses multi-sentence compression (MSC) to summarize into one single sentence originally called sentence fusion (Barzilay and McKeown, 2005; Nayeem and Chali, 2017b) .  ... 
arXiv:2102.04490v2 fatcat:awkteqi5lnc5rdddsczutdz3xu

Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization [article]

Huy Quoc To, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen, Anh Gia-Tuan Nguyen
2021 arXiv   pre-print
In this paper, we showcase how BERT can be implemented for extractive text summarization in Vietnamese on multi-document.  ...  The experiment results indicate that monolingual models produce promising results compared to other multilingual models and previous text summarizing models for Vietnamese.  ...  Since our objective is to create multi-document summaries, we concatenate all the documents in one cluster into one paragraph.  ... 
arXiv:2108.13741v3 fatcat:cw6uj67czrh3hg2dylvy6ouk74

Large-Scale Multi-Document Summarization with Information Extraction and Compression [article]

Ning Wang, Han Liu, Diego Klabjan
2022 arXiv   pre-print
Unlike existing multi-document summarization methods, our framework processes documents telling different stories instead of documents on the same topic.  ...  Lastly, we construct a total of twelve dataset variations based on CNN/Daily Mail and the NewsRoom datasets, where each document group contains a large and diverse collection of documents to evaluate the  ...  Acknowledgement We would like to express our gratitude toward Principal Financial for inspiring us with the concept of multi-document summarization with the underlying use case, and providing a dataset  ... 
arXiv:2205.00548v1 fatcat:ggbvnw5msnb3dink4yh76x5ecq

iDVS: An Interactive Multi-document Visual Summarization System [chapter]

Yi Zhang, Dingding Wang, Tao Li
2011 Lecture Notes in Computer Science  
In particular, iDVS uses a new semi-supervised document summarization method to dynamically select sentences based on users' interaction.  ...  Multi-document summarization is a fundamental tool for understanding documents.  ...  Current research on multi-document summarization often treats it as an unsupervised learning problem.  ... 
doi:10.1007/978-3-642-23808-6_37 fatcat:fpdchtoutrhfxmk6bb3l3n7cwi

Conceptual Persian Text Summarizer: An Unsupervised Model Based On Word Embedding

Mohammad Khademi, Mohammad Fakhredanesh, Seyed Hoseini
2020 ˜The œinternational Arab journal of information technology  
First we produce a word embedding based on Hamshahri2 corpus and a dictionary of word frequencies.  ...  In this work, we propose a novel unsupervised method to summarize Persian texts.  ...  [17] proposed a new multi-document multi-lingual text summarization method, based on singular value decomposition (SVD) and hierarchical clustering.  ... 
doi:10.34028/iajit/17/4/11 fatcat:osc5a7ewingybiolfpou3l73o4

Clustering Sentences with Density Peaks for Multi-document Summarization

Yang Zhang, Yunqing Xia, Yi Liu, Wenmin Wang
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
Multi-document Summarization (MDS) is of great value to many real world applications.  ...  Many scoring models are proposed to select appropriate sentences from documents to form the summary, in which the clustering-based methods are popular.  ...  Method In this work, the density peaks sentence clustering (DPSC) method is designed for multi-document summarization.  ... 
doi:10.3115/v1/n15-1136 dblp:conf/naacl/ZhangXLW15 fatcat:ore3yneqpjawtppid6km522gnm

Evaluation of Unsupervised Learning based Extractive Text Summarization Technique for Large Scale Review and Feedback Data

Jai Prakash Verma, Atul Patel
2017 Indian Journal of Science and Technology  
Unsupervised techniques based summarization systems finds representative sentences from large amount of text dataset.  ...  Graph based sentence scoring method is much efficient than other unsupervised learning techniques applied for extractive text summarization.  ...  Single and Multi-Document Summarization Systems 5,6 categorize text summariza-tion systems based on approach in which number of documents are selected for analyzing the dataset.  ... 
doi:10.17485/ijst/2017/v10i17/106493 fatcat:qwbaxugabzfclanq4m6ajxc7vy

Conceptual Text Summarizer: A new model in continuous vector space [article]

Mohammad Ebrahim Khademi, Mohammad Fakhredanesh, Seyed Mojtaba Hoseini
2018 arXiv   pre-print
First we produce a word embedding based on Hamshahri2 corpus and a dictionary of word frequencies.  ...  In this work, we propose an unsupervised method to summarize Persian texts.  ...  [38] proposed a new multi-document multi-lingual text summarization method, based on singular value decomposition (SVD) and hierarchical clustering.  ... 
arXiv:1710.10994v3 fatcat:7quvsvh7qzf55fydvcligr5kdu

Document Summarization Using Clustering and Text Analysis

Mrs. Shahana Bano, B Divyanjali, A K M L R V Virajitha, M Tejaswi
2018 International Journal of Engineering & Technology  
based on their term frequency value of the words.  ...  summarization by using clustering and text analysis.  ...  Sentence Ordering based on Cluster Adjacency [10] which describes about the sentence ordering which is not easy in multi document summarization.  ... 
doi:10.14419/ijet.v7i2.32.15740 fatcat:fozen5udbbdrxfpam5mc3xx6ti

A Survey of Unstructured Text Summarization Techniques

Sherif Elfayoumy, Jenny Thoppil
2014 International Journal of Advanced Computer Science and Applications  
and make decisions based on document contents.  ...  Others perform well in identifying and summarizing single-topic documents but their precision degrades sharply with multi-topic documents.  ...  Maximal Marginal Relevance (MMR) MMR is based on the vector space model of text retrieval [15] [17] and is well suited for query-based and multi-document summarization.  ... 
doi:10.14569/ijacsa.2014.050421 fatcat:dh6mh2brabbw7eok465x46a7fa

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.  ...  Summary Table 1 . 1 Multi-document Summarization Models based on Graph Neural Networks.  ... 
arXiv:2011.04843v3 fatcat:zfi52xxef5g2tjkaw6hgjpwa5i
« Previous Showing results 1 — 15 out of 15,833 results