تقرير
Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances
العنوان: | Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances |
---|---|
المؤلفون: | Kim, Wongyu, Ahn, Youbin, Kim, Donghyun, Lee, Kyong-Ho |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning |
الوصف: | Each utterance in multi-turn empathetic dialogues has features such as emotion, keywords, and utterance-level meaning. Feature transitions between utterances occur naturally. However, existing approaches fail to perceive the transitions because they extract features for the context at the coarse-grained level. To solve the above issue, we propose a novel approach of recognizing feature transitions between utterances, which helps understand the dialogue flow and better grasp the features of utterance that needs attention. Also, we introduce a response generation strategy to help focus on emotion and keywords related to appropriate features when generating responses. Experimental results show that our approach outperforms baselines and especially, achieves significant improvements on multi-turn dialogues. Comment: Accepted to NAACL 2022 Main Conference |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2205.03112 |
رقم الأكسشن: | edsarx.2205.03112 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |