Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance
In order to solve the problem of ineffective utilization of the semantic information between documents in the traditional multi-document extractive summarization method and the excessive redundant content in the summary result, a Khmer multi-document extractive summarization method based on hierarch...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | zho |
Published: |
Hebei University of Science and Technology
2020-12-01
|
Series: | Journal of Hebei University of Science and Technology |
Subjects: | |
Online Access: | http://xuebao.hebust.edu.cn/hbkjdx/ch/reader/create_pdf.aspx?file_no=b202006005&flag=1&journal_ |
id |
doaj-090b384f84b24434a9bf7ae5763e5233 |
---|---|
record_format |
Article |
spelling |
doaj-090b384f84b24434a9bf7ae5763e52332020-12-04T01:05:00ZzhoHebei University of Science and TechnologyJournal of Hebei University of Science and Technology1008-15422020-12-0141650851710.7535/hbkd.2020yx06005b202006005Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevanceZhaolin ZENG0Xin YAN1Bingbing YU2Feng ZHOU3Guangyi XU4Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming,Yunnan 650500,ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming,Yunnan 650500,ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming,Yunnan 650500,ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming,Yunnan 650500,ChinaYunnan Nantian Electronic Information Industry Company Limited, Kunming,Yunnan 650040,ChinaIn order to solve the problem of ineffective utilization of the semantic information between documents in the traditional multi-document extractive summarization method and the excessive redundant content in the summary result, a Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance(MMR)was proposed. Firstly, the Khmer multi-document text was input into the trained deep learning model to extract all the single-document summaries. Then, all single document summaries were iteratively merged according to a similar hierarchical waterfall method, and the improved MMR algorithm was used to reasonably select summary sentences to obtain the final multi-document summary. The experimental results show that the R1, R2, R3, RL values of the Khmer multi-document summary obtained by using the deep learning method combined with the hierarchical MMR algorithm increases by 4.31%, 5.33%, 645% and 4.26% respectively compared with other methods. The Khmer multi-document extractive summarization method based on hierarchical MMR can effectively improve the quality of Khmer multi-document summary while ensuring the diversity and difference of the summary sentences.http://xuebao.hebust.edu.cn/hbkjdx/ch/reader/create_pdf.aspx?file_no=b202006005&flag=1&journal_natural language processing; khmer; extractive summarization; deep learning; waterfall method; maximal marginal relevance(mmr) |
collection |
DOAJ |
language |
zho |
format |
Article |
sources |
DOAJ |
author |
Zhaolin ZENG Xin YAN Bingbing YU Feng ZHOU Guangyi XU |
spellingShingle |
Zhaolin ZENG Xin YAN Bingbing YU Feng ZHOU Guangyi XU Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance Journal of Hebei University of Science and Technology natural language processing; khmer; extractive summarization; deep learning; waterfall method; maximal marginal relevance(mmr) |
author_facet |
Zhaolin ZENG Xin YAN Bingbing YU Feng ZHOU Guangyi XU |
author_sort |
Zhaolin ZENG |
title |
Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance |
title_short |
Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance |
title_full |
Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance |
title_fullStr |
Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance |
title_full_unstemmed |
Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance |
title_sort |
khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance |
publisher |
Hebei University of Science and Technology |
series |
Journal of Hebei University of Science and Technology |
issn |
1008-1542 |
publishDate |
2020-12-01 |
description |
In order to solve the problem of ineffective utilization of the semantic information between documents in the traditional multi-document extractive summarization method and the excessive redundant content in the summary result, a Khmer multi-document extractive summarization method based on hierarchical maximal marginal relevance(MMR)was proposed. Firstly, the Khmer multi-document text was input into the trained deep learning model to extract all the single-document summaries. Then, all single document summaries were iteratively merged according to a similar hierarchical waterfall method, and the improved MMR algorithm was used to reasonably select summary sentences to obtain the final multi-document summary. The experimental results show that the R1, R2, R3, RL values of the Khmer multi-document summary obtained by using the deep learning method combined with the hierarchical MMR algorithm increases by 4.31%, 5.33%, 645% and 4.26% respectively compared with other methods. The Khmer multi-document extractive summarization method based on hierarchical MMR can effectively improve the quality of Khmer multi-document summary while ensuring the diversity and difference of the summary sentences. |
topic |
natural language processing; khmer; extractive summarization; deep learning; waterfall method; maximal marginal relevance(mmr) |
url |
http://xuebao.hebust.edu.cn/hbkjdx/ch/reader/create_pdf.aspx?file_no=b202006005&flag=1&journal_ |
work_keys_str_mv |
AT zhaolinzeng khmermultidocumentextractivesummarizationmethodbasedonhierarchicalmaximalmarginalrelevance AT xinyan khmermultidocumentextractivesummarizationmethodbasedonhierarchicalmaximalmarginalrelevance AT bingbingyu khmermultidocumentextractivesummarizationmethodbasedonhierarchicalmaximalmarginalrelevance AT fengzhou khmermultidocumentextractivesummarizationmethodbasedonhierarchicalmaximalmarginalrelevance AT guangyixu khmermultidocumentextractivesummarizationmethodbasedonhierarchicalmaximalmarginalrelevance |
_version_ |
1724400690914131968 |