Year: 2021
Type: preprint
Abstract: Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency modeling among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks, compared with several strong baselines.
Source: arXiv (Cornell University)
Institution: Nanjing University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3136176158