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.
Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank
A training strategy using a multilingual BERT model and learning to rank synthetic divergent examples improves detection of fine-grained semantic differences in cross-lingual NLP.
- Year
- 2020
- Venue
- EMNLP 2020 11
- Authors
- 2
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2010.03662ARXIV-DEFAULT
- TL;DR
- Semantic Scholar