Enhancing Cross-lingual Transfer via Phonemic Transcription Integration

TL;DR

This paper introduces PhoneXL, a framework that integrates phonemic transcriptions with orthographic data to improve cross-lingual transfer, especially among languages with different scripts, demonstrating consistent performance gains on CJKV language tasks.

Contribution

The paper proposes a novel phonemic-orthographic alignment framework and releases the first dataset for CJKV languages, advancing cross-lingual transfer methods beyond script similarity.

Findings

Phonemic transcriptions provide essential information beyond orthography.

Incorporating phonemic data improves cross-lingual token-level task performance.

The framework achieves consistent improvements over traditional orthographic-based models.

Abstract

Previous cross-lingual transfer methods are restricted to orthographic representation learning via textual scripts. This limitation hampers cross-lingual transfer and is biased towards languages sharing similar well-known scripts. To alleviate the gap between languages from different writing scripts, we propose PhoneXL, a framework incorporating phonemic transcriptions as an additional linguistic modality beyond the traditional orthographic transcriptions for cross-lingual transfer. Particularly, we propose unsupervised alignment objectives to capture (1) local one-to-one alignment between the two different modalities, (2) alignment via multi-modality contexts to leverage information from additional modalities, and (3) alignment via multilingual contexts where additional bilingual dictionaries are incorporated. We also release the first phonemic-orthographic alignment dataset on two token-level tasks (Named Entity Recognition and Part-of-Speech Tagging) among the understudied but interconnected Chinese-Japanese-Korean-Vietnamese (CJKV) languages. Our pilot study reveals phonemic transcription provides essential information beyond the orthography to enhance cross-lingual transfer and bridge the gap among CJKV languages, leading to consistent improvements on cross-lingual token-level tasks over orthographic-based multilingual PLMs.