Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction

Yanzeng Li, Tingwen Liu, Diying Li, Quangang Li, Jinqiao Shi, Yanqiu Wang
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:518-533, 2018.

Abstract

Opinion target extraction (OTE) is a fundamental step for sentiment analysis and opinion summarization. We analyze the difference between Chinese and the Indo-European languages family, and reduce Chinese OTE to a character-based sequence tagging task. Then we introduce two novel features for each character by distributing POS differentially and using predefined templates over contexts and dictionaries. We further propose a character-based BiLSTM-CRF model incorporating the two feature sequences aligned with the character sequence. Experimental results on real-world consumer review datasets show that our work significantly outperforms the baseline methods for Chinese OTE.

Cite this Paper


BibTeX
@InProceedings{pmlr-v95-li18d, title = {Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction}, author = {Li, Yanzeng and Liu, Tingwen and Li, Diying and Li, Quangang and Shi, Jinqiao and Wang, Yanqiu}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {518--533}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/li18d/li18d.pdf}, url = {https://proceedings.mlr.press/v95/li18d.html}, abstract = {Opinion target extraction (OTE) is a fundamental step for sentiment analysis and opinion summarization. We analyze the difference between Chinese and the Indo-European languages family, and reduce Chinese OTE to a character-based sequence tagging task. Then we introduce two novel features for each character by distributing POS differentially and using predefined templates over contexts and dictionaries. We further propose a character-based BiLSTM-CRF model incorporating the two feature sequences aligned with the character sequence. Experimental results on real-world consumer review datasets show that our work significantly outperforms the baseline methods for Chinese OTE.} }
Endnote
%0 Conference Paper %T Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction %A Yanzeng Li %A Tingwen Liu %A Diying Li %A Quangang Li %A Jinqiao Shi %A Yanqiu Wang %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-li18d %I PMLR %P 518--533 %U https://proceedings.mlr.press/v95/li18d.html %V 95 %X Opinion target extraction (OTE) is a fundamental step for sentiment analysis and opinion summarization. We analyze the difference between Chinese and the Indo-European languages family, and reduce Chinese OTE to a character-based sequence tagging task. Then we introduce two novel features for each character by distributing POS differentially and using predefined templates over contexts and dictionaries. We further propose a character-based BiLSTM-CRF model incorporating the two feature sequences aligned with the character sequence. Experimental results on real-world consumer review datasets show that our work significantly outperforms the baseline methods for Chinese OTE.
APA
Li, Y., Liu, T., Li, D., Li, Q., Shi, J. & Wang, Y.. (2018). Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:518-533 Available from https://proceedings.mlr.press/v95/li18d.html.

Related Material