Hierarchical template transformer for fine-grained sentiment controllable generation |
| |
Institution: | 1. West China Biomedical Big Data Center, West China Hospital, Sichuan University, No.37 Guoxue Alley, Chengdu 610041, China;2. Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Chengdu 610041, China;3. West China Periodicals, West China Hospital, Sichuan University, No.37 Guoxue Alley, Chengdu 610041, China;4. Department of Bile Duct Surgery, West China Hospital, Sichuan University, No.37 Guoxue Alley, Chengdu 610041, China;1. College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, China 450002;2. School of Cyber Science and Engineering, Wuhan University, Wuhan, China 430079;3. School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China 450045;4. Henan Key Laboratory of Cyberspace Situation Awareness, Zhengzhou 450001 |
| |
Abstract: | Existing methods for text generation usually fed the overall sentiment polarity of a product as an input into the seq2seq model to generate a relatively fluent review. However, these methods cannot express more fine-grained sentiment polarity. Although some studies attempt to generate aspect-level sentiment controllable reviews, the personalized attribute of reviews would be ignored. In this paper, a hierarchical template-transformer model is proposed for personalized fine-grained sentiment controllable generation, which aims to generate aspect-level sentiment controllable reviews with personalized information. The hierarchical structure can effectively learn sentiment information and lexical information separately. The template transformer uses a part of speech (POS) template to guide the generation process and generate a smoother review. To verify our model, we used the existing model to obtain a corpus named FSCG-80 from Yelp, which contains 800K samples and conducted a series of experiments on this corpus. Experimental results show that our model can achieve up to 89.93% aspect-sentiment control accuracy and generate more fluent reviews. |
| |
Keywords: | Fine-grained text generation Sentiment controllable generation Sequence-to-sequence learning Transformers |
本文献已被 ScienceDirect 等数据库收录! |
|