Work

Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning

Year: 2023

Type: conference-paper

Abstract: It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition.We introduce CLICK for controllable text generation, which needs no modification to the model architecture and facilitates out-of-thebox use of trained models.It employs a contrastive loss on sequence likelihood, which fundamentally decreases the generation probability of negative samples (i.e., generations with undesirable attributes).It also adopts a novel likelihood ranking-based strategy to construct contrastive samples from model generations.On the tasks of language detoxification, sentiment steering, and repetition reduction, we show that CLICK outperforms strong baselines of controllable text generation and demonstrate the superiority of CLICK's sample construction strategy.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2023.findings-acl.65

Authors: Chujie Zheng, Pei Ke, Zheng Zhang, Minlie Huang

Institutions: State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Viện Trí tuệ nhân tạo, Tsinghua University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Tsinghua University

Award: G7155907028