Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank

EMNLP 2020  ·  Eleftheria Briakou, Marine Carpuat ·

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.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract

Datasets


Introduced in the Paper:

REFreSD

Used in the Paper:

test WikiMatrix

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods