| 摘要: |
| 完全非自回归翻译(fully non-autoregressive translation, Fully NAT)的主要挑战在于, 如何在保持解码速度优势的同时, 达到与自回归翻译(autoregressive translation, AT)相当的翻译质量. 这是因为并行解码的特性使得Fully NAT方法难以捕捉目标端的依赖信息, 从而导致翻译质量下降. 因此, 利用源端的依赖信息来增强模型能力显得十分自然, 尤其是在句法信息已被证明能够有效提升AT方法效果的背景下. 尽管近年来这一领域取得了显著进展, 但关于在Fully NAT中应用句法信息的研究仍然有限. 通过在5个翻译基准(如workshop on machine translation, WMT)上的实验发现, 依存语法信息对Fully NAT方法非常有帮助, 可以显著提升翻译表现, 同时解码速度的损失成本也在可接受范围内. 代码开源地址https://github.com/tianxiexiaozhu77/syngec. |
| 关键词: 非自回归翻译 (NAT) 句法信息 依存关系 机器翻译 |
| DOI：10.13328/j.cnki.jos.007463 |
| 分类号:TP18 |
| 基金项目:国家自然科学基金(62206194); 江苏省自然科学基金(BK20220488) |
|
| Dependency-syntax-information-enhanced Fully Non-autoregressive Translation |
|
ZHANG Jian-Xin, GUO Pei, LI Jun-Tao, ZHANG Min
|
|
School of Computer Science and Technology, Soochow University, Suzhou 215008, China
|
| Abstract: |
| The main challenge of fully non-autoregressive translation (Fully NAT) lies in maintaining translation quality comparable to autoregressive translation (AT) while preserving the decoding speed advantage. This challenge arises from the parallel decoding nature, which prevents Fully NAT methods from capturing dependency information on the target side, leading to degraded translation quality. Therefore, enhancing the model’s ability to capture dependency information from the source side is a natural approach, especially given that syntactic information has proven effective in improving AT methods. Although significant progress has been made in this area in recent years, there has been limited research on incorporating syntactic information in Fully NAT. Through experiments on five translation benchmarks (e.g., workshop on machine translation, WMT), it is found that dependency syntax information is highly beneficial for fully NAT methods, significantly improving translation performance with a decoding speed cost that remains within an acceptable range. The code has been released at https://github.com/tianxiexiaozhu77/syngec. |
| Key words: non-autoregressive translation (NAT) syntactic information dependency relation machine translation |
