arXiv:2010.05994

Improving Text Generation with Student-Forcing Optimal Transport

Guoyin Wang, Chunyuan Li, Jianqiao Li, Hao Fu, Yuh-Chen Lin, Liqun Chen, Yizhe Zhang, Chenyang Tao, Ruiyi Zhang, Wenlin Wang, Dinghan Shen, Qian Yang, Lawrence Carin

제출 2020-10-12

원문 초록

Neural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead conditioned on previously generated tokens, resulting in what is termed exposure bias. To reduce this gap between training and testing, we propose using optimal transport (OT) to match the sequences generated in these two modes. An extension is further proposed to improve the OT learning, based on the structural and contextual information of the text sequences. The effectiveness of the proposed method is validated on machine translation, text summarization, and text generation tasks.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.