Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning

Autor:	Zheng, Chujie, Ke, Pei, Zhang, Zheng, Huang, Minlie
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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-the-box 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. Comment: Findings of ACL 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.03350 Zobrazit plný text záznamu View this record from Arxiv