BERT Cannot Align Characters
This work addresses the limitation of BERT for character-level alignment in multilingual NLP, but it is incremental as it builds on known word-level capabilities.
The paper investigated whether BERT can align characters across languages, finding that it performs well for closely related languages like English to Fake-English but poorly for more distant natural languages such as English to Greek, with performance correlating with language proximity.
In previous work, it has been shown that BERT can adequately align cross-lingual sentences on the word level. Here we investigate whether BERT can also operate as a char-level aligner. The languages examined are English, Fake-English, German and Greek. We show that the closer two languages are, the better BERT can align them on the character level. BERT indeed works well in English to Fake-English alignment, but this does not generalize to natural languages to the same extent. Nevertheless, the proximity of two languages does seem to be a factor. English is more related to German than to Greek and this is reflected in how well BERT aligns them; English to German is better than English to Greek. We examine multiple setups and show that the similarity matrices for natural languages show weaker relations the further apart two languages are.