ABSTRACT
Social network is a good resource to collect public opinions considering the diversity and variety in fashion, especially user generated content (UGC). Extracting the opinions from UGC can be the base of commercial policy, so how to extract the opinions correctly is an important problem. However, there are two problems: Are the opinions really talking about the target entities? Or the amount of opinions is enough for network volume analysis? In this study, we combine rule-based method and Semantic Role Labeling (SRL) to detect the opinion target (OTD) from UGC. In SRL task, we design a neural network model to extract the opinion words. Considering gradient vanish problem, we use highway connection to control the percentage of data. To improve the performance of SRL, we use additional features to help model learn the features between verb and other phrases. Finally, we design a rule to filter the result of SRL for OTD task. The experimental results show that our SRL model obtains 71% F1, and our method on OTD task obtains 73% precision which outperforms LTP. This research can be the basis of hot topic prediction for sponsors and helps them to decide marketing strategies
- J. Zhou and W. Xu, "End-to-end learning of semantic role labeling using recurrent neural networks," In The 53rd Annual Meeting of the Association for Computational Linguistics and The 7th International Joint Conference on Natural Language Processing, pp. 1127--1137, July 2015.Google Scholar
- Y. Zhang, G. Chen, D. Yu, K. Yao, S. Khudanpur, J. Glass, "Highway long short-term memory rnns for distant speech recognition," 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, March 2016.Google Scholar
- R.K. Srivastava, K. Greff, J. Schmidhuber, "Training very deep networks," In Advances in Neural Information Processing Systems 2015, November 2015.Google Scholar
- R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, P. Kuksa, "Natural Language Processing (Almost) from Scratch," In The Journal of Machine Learning Research, vol. 12, pp. 2493--2537, February 2011.Google ScholarDigital Library
- Y. N. Dauphin, A. Fan, M. Auli, D. Grangier, "Language modeling with gated convolutional networks," In The 34th International Conference on Machine Learning, PMLR 70:933-941, 2017.Google Scholar
- V. Punyakanok, D. Roth, W. T. Yih, "The importance of syntactic parsing and inference in semantic role labeling," Journal Computational Linguistics, vol. 34, pp. 257--287, June 2008.Google ScholarDigital Library
- L. He, K. Lee, M. Lewis, L. Zettlemoyer, "Deep Semantic Role Labeling: What Works and What's Next," In The 55th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 473--483, July 2017.Google ScholarCross Ref
- S. M. Kim, E. Hovy, "Extracting opinions, opinion holders, and topics expressed in online news media text," In The Workshop on Sentiment and Subjectivity in Text, pp. 1--8, July 2006.Google Scholar
- J. H. Wang, T. W. Ye, "Microblog Sentiment Analysis based on Opinion Target Modifying," In The 25th Conference on Computational Linguistics and Speech Processing ROCLING 2013, 2013.Google Scholar
- H. Yao, M. Li, J. Cheng, "Extraction of Chinese "Opinion target - Opinion word" Pairs Based on Part-of-speech Rules and Semantic Dependency Parsing," In The 2nd International Conference on Business and Information Management, pp. 11--14, September 2018.Google Scholar
- J. Lafferty, A. Mccallum, F.C. N. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," In The 18th International Conference on Machine Learning 2001 (ICML 2001), pp. 282--289, June 2001.Google Scholar
- M. Palmer, D. Gildea, P. Kingsbury, "The Proposition Bank: A Corpus Annotated with Semantic Roles," In Computational Linguistics Journal, vol. 20, 2005.Google Scholar
- C. H. Chang, C. H. Chang, "Multi-Stack Convolution with Gating Mechanism for Chinese Named Entity Recognition," 2018.Google Scholar
- C. L. Chou, C. H. Chang, "Named entity extraction via automatic labeling and tri-training: comparison of selection methods, " AIRS 2014, Lecture Notes in Computer Science, vol. 8870, 2014.Google Scholar
- Y. Y. Huang, C. H. Chang, C. L. Chou, "A Tool for Web NER Model Generation Using Search Snippets of Known Entities," In The Association for Computational Linguistics and Chinese Language Processing, pp. 148--163, October 2015.Google Scholar
- M. Wiegand, M. Schulder, "Opinion Holder and Target Extraction for Verb-based Opinion Predicates - The Problem is Not Solved," In The 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA 2015), pp. 148--155, September 2015.Google Scholar
- L. He, K. Lee, O. Levy, L. Zettlemoyer, "Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling," In The 56th Annual Meeting of the Association for Computational Linguistics, pp. 364--369, July 2018.Google Scholar
- K. Lee, L. He, M, Lewis, L. Zettlemoyer, "End-to-end Neural Coreference Resolution," In The 2017 Conference on Empirical Methods in Natural Language Processing, pp. 188--197, September 2017.Google ScholarCross Ref
- Y. M. Hsieh, M. H. Bai, J. S. Chang, K. J. Chen, "Improving PCFG Chinese Parsing with Context-Dependent Probability Re-estimation," In The 2nd CIPS-SIGHAN Joint Conference on Chinese Language Processing, pp. 216--221, December 2012.Google Scholar
- W. Che, Z. Li, T. Liu, "LTP: A Chinese Language Technology Platform," In Proceedings of the Coling 2010:Demonstrations, pp. 13--16, August 2010.Google Scholar
- Y. Li, T. Liu, D. Li, Q. Li, J. Shi, Y. W, "Character-based BiLSTMCRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction," In The 10th Asian Conference on Machine Learning, 2018.Google Scholar
- K. Liu, L. Xu, J. Zhao, "Opinion target extraction using word-based translation model," In The 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1346--1356, July 2012.Google Scholar
- A. Mukherjee, B. Liu, "Aspect Extraction through Semi-Supervised Modeling," In The 50th Annual Meeting of the Association for Computational Linguistics, pp. 339--348, July 2012.Google Scholar
- T. Wang, Y. Cai, H. F. Leung, R. Y. K. Lau, Q. Li, H. Min, "Product aspect extraction supervised with online domain knowledge," In Knowledge-Based Systems, vol. 71, pp. 86--100, November 2014.Google ScholarDigital Library
- G. Qiu, B. Liu, J. Bu, C. Chen, "Opinion Word Expansion and Target Extraction through Double Propagation," In The Annual Computational Linguistics, vol. 37, pp. 9--27, March 2011.Google ScholarDigital Library
- L. R. Rabiner, "A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition," In The IEEE, vol. 77, 1989.Google Scholar
- A. McCallum, D. Freitag, F. Pereira, "Maximum Entropy Markov Models for Information Extraction and Segmentation," In The 17th International Conference on Machine Learning, pp 591--598, June 2000.Google Scholar
- A. M. Popescu, O. Etzioni, "Extracting product features and opinions from reviews," In the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 339--346, October 2005.Google Scholar
- P. Liu, S., Joty, H. Meng, "Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings," In The 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1433--1443, September 2015.Google ScholarCross Ref
- S. Poria, E. Cambria, A. F. Gelbukh, "Aspect extraction for opinion mining with a deep convolutional neural network," In The Knowledge-Based System, June 2016.Google Scholar
- X. Li, L. Bing, P. Li, W. Lam, "A Unified Model for Opinion Target Extraction and Target Sentiment Prediction," In The 33rd Association for the Advancement of Artificial Intelligence, February 2019.Google Scholar
Recommendations
Joint Opinion Target and Target-oriented Opinion Words Extraction by BERT and IOT Model
SSPS '20: Proceedings of the 2020 2nd Symposium on Signal Processing SystemsIn this paper, we investigate two sub-tasks of aspect-based sentiment analysis (ABSA) through the pre-trained language model BERT, namely opinion target extraction (OTE) and target-oriented opinion words extraction (TOWE). Specifically, we build a novel ...
A framework for multi-document abstractive summarization based on semantic role labelling
We have proposed a framework for multi-document abstractive summarization based on semantic role labeling (SRL). To the best of our knowledge, SRL has not been employed for abstractive summarization.The integration of genetic algorithm with SRL based ...
Opinion Target Network and Bootstrapping Method for Chinese Opinion Target Extraction
AIRS '09: Proceedings of the 5th Asia Information Retrieval Symposium on Information Retrieval TechnologyOpinion mining systems suffer a great loss when unknown opinion targets constantly appear in newly composed reviews. Previous opinion target extraction methods typically consider human-compiled opinion targets as seeds and adopt syntactic/statistic ...
Comments