Abstract
Controlling chatbot utterance generation with multiple attributes such as personalities, emotions and dialogue acts is a practically useful but under-studied problem. We propose a novel framework called DASC that possesses strong controllability with a weighted decoding paradigm, while improving generation quality with the grounding in an attribute semantics space. Generation with multiple attributes is then intuitively implemented with an interpolation of multiple attribute embeddings, which results in substantial reduction in the model sizes. Experiments show that DASC can achieve high control accuracy in generation task with the simultaneous control of 3 aspects while also producing interesting and reasonably sensible responses, even in an out-of-distribution robustness test.- Anthology ID:
- 2023.emnlp-main.817
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13230–13243
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.817
- DOI:
- 10.18653/v1/2023.emnlp-main.817
- Cite (ACL):
- Zhiling Zhang, Mengyue Wu, and Kenny Zhu. 2023. Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13230–13243, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation (Zhang et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.817.pdf