GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation
Zhihua Wen, Zhiliang Tian, Zhen Huang, Yuxin Yang, Zexin Jian, Changjian Wang, Dongsheng Li
Abstract
Attribute-based generation methods are of growing significance in controlling the generation of large pre-trained language models (PLMs). Existing studies control the generation by (1) finetuning the model with attributes or (2) guiding the inference processing toward control signals while freezing the PLM. However, finetuning approaches infuse domain bias into generation, making it hard to generate out-of-domain texts. Besides, many methods guide the inference in its word-by-word generation, pushing the word probability to the target attributes, resulting in less fluent sentences. We argue that distilling controlling information from natural texts can produce fluent sentences while maintaining high controllability. In this paper, we propose GRAdient-guided Controllable rEtrieval (GRACE), a retrieval-augmented generation framework to facilitate the generation of fluent sentences with high attribute relevance. GRACE memorizes the semantic and attribute information from unlabeled corpora and applies a controllable retrieval to obtain desired information. For the generation, we design techniques to eliminate the domain bias from the retrieval results and integrate it into the generation model. Additionally, we propose a gradient-guided generation scheme that iteratively steers generation toward higher attribute relevance. Experimental results and quantities of examples verify the effectiveness of our method.- Anthology ID:
- 2023.findings-acl.530
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8377–8398
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.530
- DOI:
- 10.18653/v1/2023.findings-acl.530
- Cite (ACL):
- Zhihua Wen, Zhiliang Tian, Zhen Huang, Yuxin Yang, Zexin Jian, Changjian Wang, and Dongsheng Li. 2023. GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8377–8398, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation (Wen et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.findings-acl.530.pdf