论文标题
编辑：基于编辑的变压器，重新定位神经机器翻译具有软词汇约束
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints
论文作者
论文摘要
我们介绍了带有重新定位（编辑器）的基于编辑的变压器，该变压器通过无缝允许用户指定输出词汇选择中的偏好来使序列生成灵活。编辑器以迭代编辑假设生成新序列的基础，基于非自动回归序列产生的最新模型（Gu等人，2019年）。它依赖于一种新颖的重新定位操作，旨在将词汇选择与单词定位决策相关联，同时为模仿学习和在解码时的平行编辑提供高效的甲壳。从经验上讲，与Levenshtein Transformer相比，编辑器更有效地使用软词汇约束（Gu等人，2019），同时与约束光束搜索相比，加速了解码的加速度大幅度加速（Post and Vilar，2018）。与标准的罗马尼亚英语，英语和英语 - 日本机器翻译任务相比，编辑器还可以实现可比较或更好的翻译质量，并具有更快的解码速度。
We introduce an Edit-Based Transformer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice. Building on recent models for non-autoregressive sequence generation (Gu et al., 2019), EDITOR generates new sequences by iteratively editing hypotheses. It relies on a novel reposition operation designed to disentangle lexical choice from word positioning decisions, while enabling efficient oracles for imitation learning and parallel edits at decoding time. Empirically, EDITOR uses soft lexical constraints more effectively than the Levenshtein Transformer (Gu et al., 2019) while speeding up decoding dramatically compared to constrained beam search (Post and Vilar, 2018). EDITOR also achieves comparable or better translation quality with faster decoding speed than the Levenshtein Transformer on standard Romanian-English, English-German, and English-Japanese machine translation tasks.
