Style Control for Schema-Guided Natural Language Generation
Alicia Tsai, Shereen Oraby, Vittorio Perera, Jiun-Yu Kao, Yuheng Du, Anjali Narayan-Chen, Tagyoung Chung, Dilek Hakkani-Tur
Abstract
Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to simultaneously accomplish specific stylistic goals, such as response length, point-of-view, descriptiveness, sentiment, formality, and empathy. In this work, we focus on stylistic control and evaluation for schema-guided NLG, with joint goals of achieving both semantic and stylistic control. We experiment in detail with various controlled generation methods for large pretrained language models: specifically, conditional training, guided fine-tuning, and guided decoding. We discuss their advantages and limitations, and evaluate them with a broad range of automatic and human evaluation metrics. Our results show that while high style accuracy and semantic correctness are easier to achieve for more lexically-defined styles with conditional training, stylistic control is also achievable for more semantically complex styles using discriminator-based guided decoding methods. The results also suggest that methods that are more scalable (with less hyper-parameters tuning) and that disentangle context generation and stylistic variations are more effective at achieving semantic correctness and style accuracy.- Anthology ID:
- 2021.nlp4convai-1.21
- Volume:
- Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Alexandros Papangelis, Paweł Budzianowski, Bing Liu, Elnaz Nouri, Abhinav Rastogi, Yun-Nung Chen
- Venue:
- NLP4ConvAI
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 228–242
- Language:
- URL:
- https://aclanthology.org/2021.nlp4convai-1.21
- DOI:
- 10.18653/v1/2021.nlp4convai-1.21
- Cite (ACL):
- Alicia Tsai, Shereen Oraby, Vittorio Perera, Jiun-Yu Kao, Yuheng Du, Anjali Narayan-Chen, Tagyoung Chung, and Dilek Hakkani-Tur. 2021. Style Control for Schema-Guided Natural Language Generation. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 228–242, Online. Association for Computational Linguistics.
- Cite (Informal):
- Style Control for Schema-Guided Natural Language Generation (Tsai et al., NLP4ConvAI 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.nlp4convai-1.21.pdf
- Data
- SGD