Does Typological Blinding Impede Cross-Lingual Sharing?
This addresses the challenge of improving cross-lingual sharing for low-resource languages, but it is incremental as it builds on prior work with minor benefits.
The paper tackled the problem of whether models trained cross-lingually inherently learn typological cues, overshadowing explicit typological features, and found that blinding models to typology severely reduces performance, while encouraging sharing based on typology somewhat improves it.
Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candidate for this, as such data exists even for very low-resource languages. However, previous work has only found minor benefits from using typological information. Our hypothesis is that a model trained in a cross-lingual setting will pick up on typological cues from the input data, thus overshadowing the utility of explicitly using such features. We verify this hypothesis by blinding a model to typological information, and investigate how cross-lingual sharing and performance is impacted. Our model is based on a cross-lingual architecture in which the latent weights governing the sharing between languages is learnt during training. We show that (i) preventing this model from exploiting typology severely reduces performance, while a control experiment reaffirms that (ii) encouraging sharing according to typology somewhat improves performance.