计算机科学 ›› 2020, Vol. 47 ›› Issue (8): 164-170.doi: 10.11896/jsjkx.190600153

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于依赖联系分析的观点词对协同抽取

赵威1, 2, 林煜明1, 王超强1, 蔡国永1   

  1. 1 桂林电子科技大学广西可信软件重点实验室 广西 桂林 541004
    2 华东师范大学数据科学与工程学院 上海 200062
  • 出版日期:2020-08-15 发布日期:2020-08-10
  • 通讯作者: 林煜明(ymlin@guet.edu.cn)
  • 作者简介:331205121@qq.com
  • 基金资助:
    广西自然科学基金(2018GXNSFDA281049);国家自然科学基金(61662015, U1711263);广西创新驱动发展专项资金项目(桂科AA19046004);桂林电子科技大学研究生教育创新计划资助项目(2018YJCX48);广西可信软件重点实验室研究课题(kx201916)

Opinion Word-pairs Collaborative Extraction Based on Dependency Relation Analysis

ZHAO Wei1, 2, LIN Yu-ming1, WANG Chao-qiang1, CAI Guo-yong1   

  1. 1 Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China
    2 School of Data Science & Engineering, East China Normal University, Shanghai 200062, China
  • Online:2020-08-15 Published:2020-08-10
  • About author:ZHAO Wei, born in 1995, postgraduate.His main research interests include opinion mining and so on.
    LIN Yu-ming, born in 1978, Ph.D, professor.His main research interests include opinion mining, knowledge graph, and massive data management.
  • Supported by:
    This work was supported by the Guangxi Natural Science Foundation (2018GXNSFDA281049), National Natural Science Foundation of China (61662015, U1711263), Science and Technology Major Project of Guangxi Province (AA19046004) and Innovation Project of Guet Graduate Education (2018YJCX48) and Project of Guangxi Key Laboratory of Trusted Software(kx201916).

摘要: 同一类商品下, 观点词对中包含的观点目标和观点词通常有着很强的观点依赖联系, 因此可以通过对评论句子中单词间的观点依赖联系进行分析来提取观点词对。首先, 构建评论句子的依赖联系分析模型来获取评论句子中每个单词之间的依赖联系信息, 文中选择的基本模型是LSTM神经网络;然后, 假设评论句子中所包含的观点词对中的一项是已知的, 并将该已知项作为模型的注意力信息, 使得模型能够从评论句子中有重点地提取出与该已知项具有强观点依赖联系的单词或词组, 并将其作为观点词对中的另一未知项;最后, 将观点依赖联系得分最高的词对作为观点词对并输出。文中进一步设计了一种复合模型, 通过结合两种包含不同已知项信息的上述模型, 来实现在不需要提前知道已知项的情况下观点词对的挖掘。

关键词: 观点词对, 观点依赖联系分析, 注意力机制, 神经网络

Abstract: In the same category of commodities, opinion word-pairs usually have strong opinion dependence relation to the opinion targets and the opinion words contained in them.Therefore, in the extraction process of opinion word-pairs, they can be extracted by analyzing the opinion dependence relations among the words in the review sentences.Firstly, a dependency relation analysis model is constructed to obtain the dependency relation information of each word in a review sentence, and the basic model is defined as LSTM neural network.Secondly, it is assumed that one of the item that opinion word-pairs contained in review sentence is known, and the known item is used as the model’s attention information, so that the model can focus on extracting the words of phrases associated with the known item with strong opinion dependence from the review sentence as another unknown item in the opinion word-pairs.Finally, the word-pairs with the highest score of the opinion dependence relation are output as the opinion word-pairs.Then a compound model is designed to realize the mining of opinion word pairs without knowing the known items in advance by combining the two models which contain the information of different known items in the opinion word-pairs.

Key words: Opinion pair, Opinion dependency relation analysis, Attention mechanism, Neural network

中图分类号: 

  • TP391
[1] DING X, LIU B, YU P S.A holistic lexicon-based approach to opinion mining[C]∥International Conference on Web Search & Data Mining.2008:231-240.
[2] WU Y, ZHANG Q, HUANG X, et al.Phrase Dependency Parsing for Opinion Mining[C]∥Proceedings of the 2009 Confe-rence on Empirical Methods in Natural Language Processing.2009:1533-1541.
[3] XU L, LIU K, LAI S, et al.Mining Opinion Words and Opinion Targets in a Two-Stage Framework[C]∥Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics.2013:1764-1773.
[4] WU C, WU F, WU S, et al.A Hybrid Unsupervised Method for Aspect Term and Opinion Target Extraction[J].Knowledge-Based Systems, 2018:148:66-73.
[5] DANILO E, DENILSON G, IVES P, et al.Analysis of Document Pre-Processing Effects in Text and Opinion Mining[J].Information, 2018, 9(4):100.
[6] AGERRI R, RIGAU G.Language Independent Sequence Labelling for Opinion Target Extraction[J].Artificial Intelligence, 2019, 268:85-95.
[7] DING X, LIU B.Resolving Object and Attribute Coreference in Opinion Mining[C]∥The 23rd, International Conference on Computational Linguistics Proceedings of the Main Conference.2010:268-276.
[8] ALMEIDA M S C, PINTO C, et al.Martins.Aligning Opinions:Cross-Lingual Opinion Mining with Dependencies[C]∥Meeting of the Association for Computational Linguistics & Internatio-nal Joint Conference on Natural Language Processing.2015:408-418.
[9] NGUYEN Thi Thanh Thuy, NGO Xuan Bach, et al.Cross-Language Aspect Extraction for Opinion Mining[C]∥10th International Conference on Knowledge and Systems Engineering.2018:67-72.
[10] TU W, CHEUNG D, MAMOULIS N.Time-sensitive opinionmining for prediction[J].Association for the Advancement of Artificial Intelligence, 2015:4214-4215.
[11] ZHANG L, LIM S H, LIU B.Extracting and Ranking Product Features in Opinion Documents[C]∥International Conference on Computational Linguistics.2010:1462-1470.
[12] HAI Z, CHANG K, CONG G.One seed to find them all:mining opinion features via association[C]∥Proceedings of the 21st ACM International Conference on Information and Knowledge Management.2012:255-264.
[13] QIU G, LIU B, BU J, et al.Opinion Word Expansion and Target Extraction through Double Propagation[J].Computational Linguistics, 2011, 37(1):9-27.
[14] BISHAN YANG C C.Joint Inference for Fine-grained OpinionExtraction[C]∥Meeting of the Association for Computational Linguistics.2013:1640-1649.
[15] MOJICA L G, NG V.Fine-Grained Opinion Extraction withMarkov Logic Networks[C]∥2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).2015:271-276.
[16] JIANG X, LIN Y, LI Y, et al.Collective Extraction for Opinion Targets and Opinion Words from Online Reviews[C]∥7th International Conference on Cloud Computing and Big Data.2016:367-373.
[17] LIN Y, JIANG X, et al.Semi-supervised collective extraction of opinion target and opinion word from online reviews based on active labeling[J].Journal of Intelligent and Fuzzy Systems, 2017, 33(6):3949-3958.
[18] WANG H, ZHANG C, YIN H, et al.A Unified Framework for Fine-Grained Opinion Mining from Online Reviews[C]∥49th Hawaii International Conference on System Sciences (HICSS).2016:1134-1143.
[19] LADDHA A, MUKHERJEE A.Aspect Specific Opinion Ex-pression Extraction using Attention based LSTM-CRF Network[J].CoRR abs.2019:1902.02709.
[1] 余雪勇, 陈涛. 边缘计算场景中基于虚拟映射的隐私保护卸载算法[J]. 计算机科学, 2021, 48(1): 65-71.
[2] 单美静, 秦龙飞, 张会兵. L-YOLO:适用于车载边缘计算的实时交通标识检测模型[J]. 计算机科学, 2021, 48(1): 89-95.
[3] 何彦辉, 吴桂兴, 吴志强. 基于域适应的X光图像的目标检测[J]. 计算机科学, 2021, 48(1): 175-181.
[4] 赵佳琦, 王瀚正, 周勇, 张迪, 周子渊. 基于多尺度与注意力特征增强的遥感图像描述生成方法[J]. 计算机科学, 2021, 48(1): 190-196.
[5] 刘洋, 金忠. 一种结合非局部和多区域注意力机制的细粒度图像识别方法[J]. 计算机科学, 2021, 48(1): 197-203.
[6] 李亚男, 胡宇佳, 甘伟, 朱敏. 基于深度学习的miRNA靶位点预测研究综述[J]. 计算机科学, 2021, 48(1): 209-216.
[7] 王瑞平, 贾真, 刘畅, 陈泽威, 李天瑞. 基于DeepFM的深度兴趣因子分解机网络[J]. 计算机科学, 2021, 48(1): 226-232.
[8] 张艳梅, 楼胤成. 基于深度神经网络的庞氏骗局合约检测方法[J]. 计算机科学, 2021, 48(1): 273-279.
[9] 王润正, 高见, 黄淑华, 仝鑫. 基于知识蒸馏的恶意代码家族检测方法[J]. 计算机科学, 2021, 48(1): 280-286.
[10] 庄世杰, 於志勇, 郭文忠, 黄昉菀. 基于Zoneout的跨尺度循环神经网络及其在短期电力负荷预测中的应用[J]. 计算机科学, 2020, 47(9): 105-109.
[11] 张佳嘉, 张小洪. 多分支卷积神经网络肺结节分类方法及其可解释性[J]. 计算机科学, 2020, 47(9): 129-134.
[12] 朱玲莹, 桑庆兵, 顾婷婷. 基于视差信息的无参考立体图像质量评价[J]. 计算机科学, 2020, 47(9): 150-156.
[13] 赵钦炎, 李宗民, 刘玉杰, 李华. 基于信息熵的级联Siamese网络目标跟踪[J]. 计算机科学, 2020, 47(9): 157-162.
[14] 游兰, 韩雪薇, 何正伟, 肖丝雨, 何渡, 潘筱萌. 基于改进Seq2Seq的短时AIS轨迹序列预测模型[J]. 计算机科学, 2020, 47(9): 169-174.
[15] 崔彤彤, 王桂玲, 高晶. 基于1DCNN-LSTM的船舶轨迹分类方法[J]. 计算机科学, 2020, 47(9): 175-184.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .