TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data

TL;DR

TransMI is a framework that leverages existing multilingual pretrained language models to effectively handle transliterated data across scripts without retraining, significantly improving crosslingual transfer performance.

Contribution

It introduces a simple, training-free method to adapt mPLMs for transliterated data by transliterating vocabularies and merging embeddings, enabling effective cross-script transfer.

Findings

TransMI improves crosslingual transfer by 3% to 34%.

It preserves the ability to handle non-transliterated data.

The framework is applicable to multiple strong mPLMs.

Abstract

Transliterating related languages that use different scripts into a common script is effective for improving crosslingual transfer in downstream tasks. However, this methodology often makes pretraining a model from scratch unavoidable, as transliteration brings about new subwords not covered in existing multilingual pretrained language models (mPLMs). This is undesirable because it requires a large computation budget. A more promising way is to make full use of available mPLMs. To this end, this paper proposes a simple but effective framework: Transliterate-Merge-Initialize (TransMI). TransMI can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training. TransMI has three stages: (a) transliterate the vocabulary of an mPLM into a common script; (b) merge the new vocabulary with the original vocabulary; and (c) initialize the embeddings of the new subwords. We apply TransMI to three strong recent mPLMs. Our experiments demonstrate that TransMI not only preserves the mPLM's ability to handle non-transliterated data, but also enables it to effectively process transliterated data, thereby facilitating crosslingual transfer across scripts. The results show consistent improvements of 3% to 34% for different mPLMs and tasks. We make our code and models publicly available at \url{https://github.com/cisnlp/TransMI}.