ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters

Vipul Kumar Rathore, Rajdeep Dhingra, Parag Singla, Mausam .

Submission Type: Regular Long Paper

Submission Track: Multilinguality and Linguistic Diversity

Keywords: Multilinguality, Low Resource Languages, Parameter-Efficient Fine-Tuning (PEFT)

TL;DR: We propose a strong method that ensembles Language Adapters at train and test-time for Zero-shot transfer to Low Resource Languages

Abstract:

We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the target LA or LA of another related language. Training target LA requires unlabeled data, which may not be readily available for low resource *unseen* languages: those that are neither seen by the underlying multilingual language model (e.g., mBERT), nor do we have any (labeled or unlabeled) data for them.

We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL.
Extensive experimentation across four language groups, covering 15 unseen target languages, demonstrates improvements of up to 3.2 average F1 points over standard fine-tuning and other strong baselines on POS tagging and NER tasks. We also extend ZGUL to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language. We find that ZGUL continues to outperform baselines in these settings too.

Submission Number: 3958