Does Typological Blinding Impede Cross-Lingual Sharing?

Johannes Bjerva, Isabelle Augenstein

Multilinguality Short paper Paper

Gather-3E: Apr 23, Gather-3E: Apr 23 (13:00-15:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in separate windows.

Abstract: 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.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EACL2021

Similar Papers

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation
Kemal Kurniawan, Lea Frermann, Philip Schulz, Trevor Cohn,
Interpretability for Morphological Inflection: from Character-level Predictions to Subword-level Rules
Tatyana Ruzsics, Olga Sozinova, Ximena Gutierrez-Vasques, Tanja Samardzic,
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks
Jimin Sun, Hwijeen Ahn, Chan Young Park, Yulia Tsvetkov, David R. Mortensen,