0

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
Attribution policy →

Abstract

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.

Authors

2