What do Language Representations Really Represent?
This work addresses the problem of interpreting language representations for linguists and NLP researchers, providing insights into translation effects and fostering interaction between NLP and linguistic typology, though it is incremental in nature.
The paper investigates what type of similarity is captured by language representations learned from multilingual text corpora, finding that structural similarity between languages correlates most strongly with representation similarity, while genetic relationships are a confounding factor.
A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words end up with similar representations. If the corpus is multilingual, the same model can be used to learn distributed representations of languages, such that similar languages end up with similar representations. We show that this holds even when the multilingual corpus has been translated into English, by picking up the faint signal left by the source languages. However, just like it is a thorny problem to separate semantic from syntactic similarity in word representations, it is not obvious what type of similarity is captured by language representations. We investigate correlations and causal relationships between language representations learned from translations on one hand, and genetic, geographical, and several levels of structural similarity between languages on the other. Of these, structural similarity is found to correlate most strongly with language representation similarity, while genetic relationships---a convenient benchmark used for evaluation in previous work---appears to be a confounding factor. Apart from implications about translation effects, we see this more generally as a case where NLP and linguistic typology can interact and benefit one another.