Simultaneous machine translation (SiMT) is a challenging task that requires
starting translation before the full source sentence is available.
Prefix-to-prefix framework is often applied to SiMT, which learns to predict
target tokens using only a partial source prefix. However, due to the word
order difference between languages, misaligned prefix pairs would make SiMT
models suffer from serious hallucination problems, i.e. target outputs that are
unfaithful to source inputs. Such problems can not only produce target tokens
that are not supported by the source prefix, but also hinder generating the
correct translation by receiving more source words. In this work, we propose a
Confidence-Based Simultaneous Machine Translation (CBSiMT) framework, which
uses model confidence to perceive hallucination tokens and mitigates their
negative impact with weighted prefix-to-prefix training. Specifically,
token-level and sentence-level weights are calculated based on model confidence
and acted on the loss function. We explicitly quantify the faithfulness of the
generated target tokens using the token-level weight, and employ the
sentence-level weight to alleviate the disturbance of sentence pairs with
serious word order differences on the model. Experimental results on MuST-C
English-to-Chinese and WMT15 German-to-English SiMT tasks demonstrate that our
method can consistently improve translation quality at most latency regimes,
with up to 2 BLEU scores improvement at low latency.

我们提出了一种基于置信度的同传机器翻译框架（CBSiMT），通过利用模型置信度来察觉幻觉标记，并通过加权的前缀对前缀训练来减轻它们的负面影响。实验结果表明我们的方法可以在大多数延迟范围内持续提高翻译质量，低延迟时提高 2 个 BLEU 分数。