Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2022, Vol. 16 Issue (6) : 166333    https://doi.org/10.1007/s11704-021-0561-z
RESEARCH ARTICLE
Exploiting comments information to improve legal public opinion news abstractive summarization
Yuxin HUANG1,2, Zhengtao YU1,2(), Yan XIANG1,2, Zhiqiang YU1,2, Junjun GUO1,2
1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
2. Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming 650500, China
 Download: PDF(10044 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

Automatically generating a brief summary for legal-related public opinion news (LPO-news, which contains legal words or phrases) plays an important role in rapid and effective public opinion disposal. For LPO-news, the critical case elements which are significant parts of the summary may be mentioned several times in the reader comments. Consequently, we investigate the task of comment-aware abstractive text summarization for LPO-news, which can generate salient summary by learning pivotal case elements from the reader comments. In this paper, we present a hierarchical comment-aware encoder (HCAE), which contains four components: 1) a traditional sequenceto-sequence framework as our baseline; 2) a selective denoising module to filter the noisy of comments and distinguish the case elements; 3) a merge module by coupling the source article and comments to yield comment-aware context representation; 4) a recoding module to capture the interaction among the source article words conditioned on the comments. Extensive experiments are conducted on a large dataset of legal public opinion news collected from micro-blog, and results show that the proposed model outperforms several existing state-of-the-art baseline models under the ROUGE metrics.
Keywords legal public opinion news      abstractive summarization      comment      comment-aware context      case elements      bi-directional attention     
Corresponding Author(s): Zhengtao YU   
Just Accepted Date: 12 July 2021   Issue Date: 12 January 2022
 Cite this article:   
Yuxin HUANG,Zhengtao YU,Yan XIANG, et al. Exploiting comments information to improve legal public opinion news abstractive summarization[J]. Front. Comput. Sci., 2022, 16(6): 166333.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-021-0561-z
https://academic.hep.com.cn/fcs/EN/Y2022/V16/I6/166333
Fig.1  The overview of HCAE model
Fig.2  The architecture of dual-channel selective denoising module
Fig.3  The structure of the bi-directional attention module
Dataset Training set Validation set Test set
#(examples) 109,301 1,000 1,000
#(articleWords) 7.74M 71.9K 71.2K
#(summWords) 1.32M 12.1K 12.2K
AvgArticleLen 70.8 71.86 71.21
AvgSummLen 12.08 12.11 12.20
Tab.1  Data statistics for our dataset. #(x) denotes the number of x, e.g., #(examples) is the number of samples of corresponding datasets. AvgArticleLen is the average input article length and AvgSummLen is the average summary length
Fig.4  Statistics of comments in LPO-news corpus. (a) The distribution of comments; (b) The distribution of comment scores
Models RG-1 RG-2 RG-L
RA 28.15 11.85 27.01
SEASS 28.54 12.11 27.35
CGU 28.37 12.34 27.31
PG 29.99 12.39 27.90
KIGN 30.26 12.31 28.04
KCS 30.41 12.18 28.27
S2S_LSTM 27.85 11.71 26.34
S2S_Transformer 27.56 11.58 27.18
HCAE 30.80 12.66 28.60
Tab.2  Full-length ROUGE F1 evaluation results on the test set. All the ROUGE scores have a 95% confidence interval of at most ±0.5 as calculated by the official ROUGE script
Models RG-1 RG-2 RG-L
w/o Denosing 25.06 10.37 24.33
w/o Merging 21.65 7.72 19.19
w/o Recoding 28.65 11.79 27.81
HCAE 30.80 12.66 28.60
Tab.3  Full-length ROUGE F1 evaluation results of different ablation models on the test set
Merge approaches RG-1 RG-2 RG-L
Concatenation 30.46 12.14 28.32
Selective Gate 29.14 11.65 28.18
Bi-Directional Attention 30.80 12.66 28.60
Tab.4  Full-length ROUGE F1 results of different merge approaches on the test set
Num Random Comment score
RG-1 RG-2 RG-L RG-1 RG-2 RG-L
1 26.24 10.77 25.69 27.93 11.92 26.77
3 28.86 11.06 26.47 30.28 12.50 28.09
5 29.57 11.64 27.15 31.24 12.92 29.17
10 30.11 12.37 28.42 30.98 12.90 28.78
20 30.24 12.63 28.39 30.69 12.75 28.46
Tab.5  Full-length ROUGE F1 results of different merge approaches on the test set
1 R Nallapati, B W Zhou, D C Santos, Ç Guçehre, B Xiang. Abstractive text summarization using sequence-to-sequence RNNs and beyond. In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning. 2016, 280– 290
2 J T Gu, Z D Lu, H Li, V O Li. Incorporating copying mechanism in sequence-to-sequence learning. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016, 1631− 1640
3 Q Y Zhou, N Yang, F R Wei, M Zhou. Selective encoding for abstractive sentence summarization. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017, 1095− 1104
4 H Y Xu , Z Q Wang , Y F Zhang , X L Weng , Z J Wang , G D Zhou . Document structure model for survey generation using neural network. Frontiers of Computer Science, 2021, 15( 4): 1– 10
5 A Jadhav, V Rajan. Extractive summarization with SWAP-NET: Sentences and words from alternating pointer networks. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018, 142– 151
6 H Wang, X Wang, W H Xiong, M Yu, X X Guo, S Y Chang, W Y Wang. Self-supervised learning for contextualized extractive summarization. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019, 2221− 2227
7 S W Cho, L Lebanoff, H Foroosh, F Liu. Improving the similarity measure of determinantal point processes for extractive multi-document summarization. 2019, arXiv preprint arXiv: 1906.00072
8 W X Zhao , J R Wen , X M Li . Generating timeline summaries with social media attention. Frontiers of Computer Science, 2016, 10( 4): 702– 716
9 A M Rush, S Chopra, J Weston. A neural attention model for abstractive sentence summarization. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015, 379– 389
10 O Vinyals, M Fortunato, N Jaitly. Pointer networks. Advances in neural information processing systems, 2015, 2692− 2700
11 A See, P J Liu, C D Manning. Get to the point: Summarization with pointer-generator networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017, 1073− 1083
12 K Q Song, L Zhao, F Liu. Structure-infused copy mechanisms for abstractive summarization. 2018, arXiv preprint arXiv: 1806.05658
13 X X Zhang, M Lapata. Sentence simplification with deep reinforcement learning. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017, 584– 594
14 R Pasunuru, M Bansal. Multi-reward reinforced summarization with saliency and entailment. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018, 646– 653
15 W Y Zeng, W J Luo, S Fidler, R Urtasun. Efficient summarization with read-again and copy mechanism. 2016, arXiv preprint arXiv: 1611.03382
16 Y C Xia, F Tian, L J Wu, J X Lin, T Qin, N H Yu, T Y Liu. Deliberation networks: Sequence generation beyond one-pass decoding. Advances in Neural Information Processing Systems, 2017, 1784− 1794
17 Y C Chen, M Bansal. Fast abstractive summarization with reinforce-selected sentence rewriting. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018, 675– 686
18 W T Hsu, C K Lin, M Y Lee, K R Min, J Tang, M Sun. A unified model for extractive and abstractive summarization using inconsistency loss. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018, 132– 141
19 Hu M S, Sun A X, Lim E P. Comments-oriented document summarization: understanding documents with readers’ feedback. In: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval. 2008, 291–298
20 Z Yang, K K Cai, J Tang, L Zhang, Z Su, J Z Li. Social context summarization. In: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval. 2011, 255– 264
21 M T Nguyen, C X Tran, D V Tran, M L Nguyen. Solscsum: A linked sentence-comment dataset for social context summarization. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 2016, 2409− 2412
22 M T Nguyen, D V Lai, P K Do, D V Tran, M Le Nguyen. Vsolscsum: Building a vietnamese sentence-comment dataset for social context summarization. In: Proceedings of the 12th Workshop on Asian Language Resources (ALR12). 2016, 38– 48
23 P J Li, L D Bing, W Lam, H Li, Y Liao. Reader-aware multi-document summarization via sparse coding. In: Proceedings of Twenty-Fourth International Joint Conference on Artificial Intelligence. 2015
24 P J Li, L D Bing, W Lam. Reader-aware multi-document summarization: An enhanced model and the first dataset. In: Proceedings of the Workshop on New Frontiers in Summarization. 2017, 91– 99
25 S Gao, X Y Chen, P J Li, Z C Ren, L D Bing, D Y Zhao, R Yan. Abstractive text summarization by incorporating reader comments. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 6399− 6406
26 S Gao, X Y Chen, Z C Ren, D Y Zhao, R Yan. From standard summarization to new tasks and beyond: Summarization with manifold information. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20. 2020, 4854− 4860
27 P Bhattacharya, K Hiware, S Rajgaria, N Pochhi, K Ghosh, S Ghosh. A comparative study of summarization algorithms applied to legal case judgments. In: Proceedings of European Conference on Information Retrieval. 2019, 413– 428
28 D Jain , M D Borah , A Biswas . Summarization of legal documents: Where are we now and the way forward. Computer Science Review, 2021, 40 : 100388–
29 B Hachey , C Grover . Extractive summarisation of legal texts. Artificial Intelligence and Law, 2006, 14( 4): 305– 345
30 R Kumar , K Raghuveer . Legal document summarization using latent dirichlet allocation. Int. J. of Computer Science and Telecommunications, 2012, 3 : 114– 117
31 F Galgani, P Compton, A Hoffmann. Combining different summarization techniques for legal text. In: Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data. 2012, 115– 123
32 H R Acharya , A D Bhat , K Avinash , R Srinath . Legonet-classification and extractive summarization of indian legal judgments with capsule networks and sentence embeddings. Journal of Intelligent & Fuzzy Systems, 2020, ( Preprint): 1– 10
33 A Elnaggar, C Gebendorfer, I Glaser, F Matthes. Multi-task deep learning for legal document translation, summarization and multi-label classification. In: Proceedings of the 2018 Artificial Intelligence and Cloud Computing Conference. 2018, 9– 15
34 L Manor, J J Li. Plain English summarization of contracts. In: Proceedings of the Natural Legal Language Processing Workshop 2019. 2019, 1– 11
35 P Y Han , S X Gao , Z T Yu , Y X Huang , J J Guo . Case-involved public opinion news summarization with case elements guidance. Journal of Chinese Information Processing, 2020, 34( 5): 56– 63
36 Y X Huang , Z T Yu , J J Guo , Z Q Yu , Y T Xian . Legal public opinion news abstractive summarization by incorporating topic information. International Journal of Machine Learning and Cybernetics, 2020, 1– 12
37 S Hochreiter, J Schmidhuber. Lstm can solve hard long time lag problems. Advances in neural information processing systems, 1997, 473– 479
38 K Wang, X J Quan, R Wang. BiSET: Bi-directional selective encoding with template for abstractive summarization. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019, 2153− 2162
39 N Kalchbrenner, E Grefenstette, P Blunsom. A convolutional neural network for modelling sentences. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2014, 655– 665
40 M Seo, A Kembhavi, A Farhadi, H Hajishirzi. Bidirectional attention flow for machine comprehension. 2016, arXiv preprint arXiv: 1611.01603
41 C Gulcehre, S Ahn, R Nallapati, B W Zhou, Y Bengio. Pointing the unknown words. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016, 140– 149
42 Y Zhang, Z T Yu, C L Mao, Y X Huang, S X Gao. Correlation analysis of law-related news combining bidirectional attention flow of news title and body. Journal of Intelligent & Fuzzy Systems, (Preprint): 1– 13
43 C Y Lin. ROUGE: A package for automatic evaluation of summaries. Text Summarization Branches Out, 2004, 74– 81
44 P Adam, G Sam, C Soumith, C Gregory, Y Edward, D Zachary, L Ze-Ming, D Alban, A Luca, L Adam. Automatic differentiation in pytorch. In: Proceedings of Neural Information Processing Systems. 2017
45 Z K Hu, X Li, C C Tu, Z Y Liu, M S Sun. Few-shot charge prediction with discriminative legal attributes. In: Proceedings of the 27th International Conference on Computational Linguistics. 2018, 487– 498
46 D P Kingma, J Ba. Adam: A method for stochastic optimization. 2014, arXiv preprint arXiv: 1412.6980
47 J Y Lin, X Sun, S M Ma, Q Su. Global encoding for abstractive summarization. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2018, 163– 169
48 W R Xu , C L Li , M H Lee , C Zhang . Multi-task learning for abstractive text summarization with key information guide network. EURASIP Journal on Advances in Signal Processing, 2020, 2020 : 1– 11
49 H R Li, J N Zhu, J J Zhang, C Q Zong, X D He. Keywords-guided abstractive sentence summarization. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 8196− 8203
50 A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, A N Gomez, L Kaiser, I Polosukhin. Attention is all you need. Advances in Neural Information Processing Systems 30, 2017, 5998− 6008
51 G Klein, Y Kim, Y T Deng, V Nguyen, J Senellart, A Rush. OpenNMT: Neural machine translation toolkit. In: Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Papers). 2018, 177– 184
[1] Wenhao ZHENG, Hongyu ZHOU, Ming LI, Jianxin WU. CodeAttention: translating source code to comments by exploiting the code constructs[J]. Front. Comput. Sci., 2019, 13(3): 565-578.
[2] Tianyi WANG,Yang CHEN,Yi WANG,Bolun WANG,Gang WANG,Xing LI,Haitao ZHENG,Ben Y. ZHAO. The power of comments: fostering social interactions in microblog networks[J]. Front. Comput. Sci., 2016, 10(5): 889-907.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed