[1]ZHOU Hao,WANG Li.Chinese opinion target extraction based on fusion of semantic and syntactic information[J].CAAI Transactions on Intelligent Systems,2019,14(1):171-178.[doi:10.11992/tis.201809029]
Copy

Chinese opinion target extraction based on fusion of semantic and syntactic information

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 14 Number of periods: 2019 1 Page number: 171-178 Column: 学术论文—自然语言处理与理解 Public date: 2019-01-05
Title:
Chinese opinion target extraction based on fusion of semantic and syntactic information
Author(s):
ZHOU Hao1;  WANG Li2
1. College of Information and Computer Science, Taiyuan University of Technology, Jinzhong 030600, China;
2. College of Big Data, Taiyuan University of Technology, Jinzhong 030600, China
Keywords:
Chinese opinion target; semantic; syntactic; sequence labeling; bidirectional long short-term memory; conditional random field; extraction model
CLC:
TP391
DOI:
10.11992/tis.201809029
Abstract:
The regular method of Chinese opinion target extraction has poor accuracy, and it ignores Chinese semantics and syntactic information. Therefore, a Chinese opinion target extraction model that combines semantic and syntactic information has been proposed. On the basis of the original word vector, the model strengthens the semantic features by optimizing the character meaning strategy, so as to make up for the internal information between the ignored characters and words, and through part-of-speech sequence annotation, the word-of-speech information of the sentence is characterized, and it represents the input syntactic information in depth. Through the bidirectional long short-term memory and the conditional random field, the deviation of the labeled label is avoided, improving the extraction accuracy. The model was validated on the BDCI2017 dataset. When compared with a unincorporated semantics and grammar extraction model, the accuracy of Chinese keyword and sentiment extraction increased by 2.1% and 1.68%, respectively. The accuracy of joint extraction was 77.16%, indicating a good effect on Chinese opinion target extraction.
References:
[1] QIU Guang, LIU Bing, BU Jiajun, et al. Expanding domain sentiment lexicon through double propagation[C]//Proceedings of the 21st International Jont Conference on Artifical Intelligence. Pasadena, USA, 2009:1199-1204.
[2] ZHAI Zhongwu, XU Hua, KANG Bada, et al. Exploiting effective features for Chinese sentiment classification[J]. Expert systems with applications, 2011, 38(8):9139-9146.
[3] ZHANG Lei, LIU Bing, LIM S H, et al. Extracting and ranking product features in opinion documents[C]//Proceedings of the 23rd International Conference on Computational Linguistics:Posters. Beijing, China, 2010:1462-1470.
[4] 孟园, 王洪伟. 中文评论产品特征与观点抽取方法研究[J]. 现代图书情报技术, 2016, 32(2):16-24 MENG Yuan, WANG Hongwei. Extracting product feature and user opinion from Chinese reviews[J]. Data analysis and knowledge discovery, 2016, 32(2):16-24
[5] 廖祥文, 陈兴俊, 魏晶晶, 等. 基于多层关系图模型的中文评价对象与评价词抽取方法[J]. 自动化学报, 2017, 43(3):462-471 LIAO Xiangwen, CHEN Xingjun, WEI Jingjing, et al. A multi-layer relation graph model for extracting opinion targets and opinion words[J]. Acta automatica sinica, 2017, 43(3):462-471
[6] 丁晟春, 吴婧婵媛, 李霄. 基于CRFs和领域本体的中文微博评价对象抽取研究[J]. 中文信息学报, 2016, 30(4):159-166 DING Shengchun, WU Jingchanyuan, LI Xiao. Opinion targets extraction from Chinese microblogs based on conditional random fields and domain ontology[J]. Journal of Chinese information processing, 2016, 30(4):159-166
[7] PENG Nanyun, DREDZE M. Improving named entity recognition for Chinese social media with word segmentation representation learning[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany, 2016:149-155.
[8] MA Xuezhe, HOVY E. End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany, 2016:1064-1074.
[9] PHAM T H, LE-HONG P. End-to-end recurrent neural network models for Vietnamese named entity recognition:word-level vs. Character-level[C]//Proceedings of the 15th International Conference of the Pacific Association for Computational Linguistics. Yangon, Myanmar, 2017:219-232.
[10] JEBBARA S, CIMIANO P. Improving opinion-target extraction with character-level word embeddings[C]//Proceedings of the 1st Workshop on Subword and Character Level Models in NLP. Copenhagen, Denmark, 2017:159-167.
[11] HAMMERTON J. Named entity recognition with long short-term memory[C]//Proceedings of the 7th Conference on Natural Language Learning at HLT-NAACL 2003. Edmonton, Canada, 2003:172-175.
[12] CHEN Xinxiong, XU Lei, LIU Zhiyuan, et al. Joint learning of character and word embeddings[C]//Proceedings of the 24th International Conference on Artificial Intelligence. Buenos Aires, Argentina, 2015:1236-1242.
[13] YU Mo, DREDZE M. Improving lexical embeddings with semantic knowledge[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, USA, 2014:545-550.
[14] DOS SANTOS C N, GATTI M. Deep convolutional neural networks for sentiment analysis of short texts[C]//Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics. Dublin, Ireland, 2014:69-78.
[15] ZHENG Xiaoqing, CHEN Hanyang, XU Tianyu. Deep learning for Chinese word segmentation and POS tagging[C]//Proceedings of 2013 Conference on Empirical Methods in Natural Language Processing. Seattle, USA, 2013:647-657.
[16] SPITKOVSKY V I, ALSHAWI H, JURAFSKY D, et al. Viterbi training improves unsupervised dependency parsing[C]//Proceedings of the 14th Conference on Computational Natural Language Learning. Uppsala, Sweden, 2010:9-17.
[17] YADAV V, BETHARD S. A survey on recent advances in named entity recognition from deep learning models[C]//Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, USA, 2018:2145-2158.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems