Using Centroid Keywords and Word Mover's Distance for Single Document Extractive Summarization

被引：1

作者：

Seitkali, Dauken ^{[1
]}

Mussabayev, Rustam ^{[1
]}

机构：

[1] Inst Informat & Computat Technol, 125 Pushkina, Alma Ata 050010, Kazakhstan

来源：

NLPIR 2019: 2019 3RD INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING AND INFORMATION RETRIEVAL | 2019年

关键词：

Centroid; WMD; word2vec; extractive summarization;

D O I：

10.1145/3342827.3342852

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents unsupervised method of single document extractive summarization. The main idea behind the method is in selecting sentences based on Word Mover's Distance Similarity between each sentence and set of centroid keywords. This approach leverages both compositional property of word embeddings and advantages of recently discovered powerful text to text distance metric. ROUGE results on DUC 2002 data set showed that quality of produced summaries can compete with well-known state of the art systems. In this work we also discuss limitations of gold summaries in evaluating quality of summarization systems.

引用

页码：149 / 152

页数：4

共 50 条

[21] Topic Modeling on User Stories using Word Mover's Distance
Guelle, Kim Julian
Ford, Nicholas
Ebel, Patrick
Brokhausen, Florian
Vogelsang, Andreas
[J]. 2020 IEEE SEVENTH INTERNATIONAL WORKSHOP ON ARTIFICIAL INTELLIGENCE FOR REQUIREMENTS ENGINEERING (AIRE 2020), 2020, : 52 - 60
[22] Extractive Text Summarization using Word Vector Embedding
Jain, Aditya
Bhatia, Divij
Thakur, Manish K.
[J]. 2017 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND DATA SCIENCE (MLDS 2017), 2017, : 51 - 55
[23] Gibberish, Assistant, or Master? Using Tweets Linking to News for Extractive Single -Document Summarization
Wei, Zhongyu
Gao, Wei
[J]. SIGIR 2015: PROCEEDINGS OF THE 38TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2015, : 1003 - 1006
[24] Text document summarization using word embedding
Mohd, Mudasir
Jan, Rafiya
Shah, Muzaffar
[J]. EXPERT SYSTEMS WITH APPLICATIONS, 2020, 143 (143)
[25] Topic Mover's Distance Based Document Classification
Wu, Xinhui
Li, Hui
[J]. 2017 17TH IEEE INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT 2017), 2017, : 1998 - 2002
[26] A topic modeled unsupervised approach to single document extractive text summarization
Srivastava, Ridam
Singh, Prabhav
Rana, K. P. S.
Kumar, Vineet
[J]. KNOWLEDGE-BASED SYSTEMS, 2022, 246
[27] Extractive Multi-document Summarization using K-means, Centroid-based Method, MMR, and Sentence Position
Hai Cao Manh
Huong Le Thanh
Tuan Luu Minh
[J]. SOICT 2019: PROCEEDINGS OF THE TENTH INTERNATIONAL SYMPOSIUM ON INFORMATION AND COMMUNICATION TECHNOLOGY, 2019, : 29 - 35
[28] Analyzing Preprocessing Settings for Urdu Single-document Extractive Summarization
Humayoun, Muhammad
Yu, Hwanjo
[J]. LREC 2016 - TENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2016, : 3686 - 3693
[29] Graph-based extractive text summarization based on single document
Avaneesh Kumar Yadav
Rama Shankar Ranvijay
Ashish Kumar Yadav
[J]. Multimedia Tools and Applications, 2024, 83 : 18987 - 19013
[30] Multi-document extractive summarization using semantic graph
del Camino Valle, Oleyda
Simon-Cuevas, Alfredo
Valladares-Valdes, Eduardo
Olivas, Jose A.
Romero, Francisco P.
[J]. PROCESAMIENTO DEL LENGUAJE NATURAL, 2019, (63): : 103 - 110

← 1 2 3 4 5 →