Detecting fine-grained differences in content conveyed in different languages
matters for cross-lingual NLP and multilingual corpora analysis, but it is a
challenging machine learning problem since annotation is expensive and hard to
scale. This work improves the prediction and annotation of fine-grained
semantic divergences. We introduce a training strategy for multilingual BERT
models by learning to rank synthetic divergent examples of varying granularity.
We evaluate our models on the Rationalized English-French Semantic Divergences,
a new dataset released with this work, consisting of English-French
sentence-pairs annotated with semantic divergence classes and token-level
rationales. Learning to rank helps detect fine-grained sentence-level
divergences more accurately than a strong sentence-level similarity model,
while token-level predictions have the potential of further distinguishing
between coarse and fine-grained divergences.

本文介绍了一个训练多语言 BERT 模型的策略，通过学习排列变异的不同粒度的合成样本来提高细粒度语义差异的预测和注释。本文还推出一个新的数据集，旨在评估我们的模型在英语 - 法语两种语言之间的语义分歧上的标注效果。结果表明，相对于强的句子级相似度模型，学习排列有助于更准确地检测细粒度句子级分歧，而令牌级别的预测具有进一步区分粗细颗粒差异的潜力。