Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging
Keywords: cross-lingual transfer, multilingual evaluation, typology
TL;DR: We investigate the roles of typology, training data and architecture choice in choosing a transfer language for crosslingual transfer.
Abstract: Cross-lingual transfer learning is an invaluable tool for overcoming data scarcity, yet selecting a suitable transfer language remains a challenge. The precise roles of linguistic typology, training data, and model architecture in transfer language choice are not fully understood. We take a holistic approach, examining how both dataset-specific and fine-grained typological features influence transfer language selection for part-of-speech tagging, considering two different sources for morphosyntactic features. While previous work examines these dynamics in the context of bilingual biLSTMS, we extend our analysis to a more modern transfer learning pipeline: zero-shot prediction with pretrained multilingual models. We train a series of transfer language ranking systems and examine how different feature inputs influence ranker performance across architectures. Word overlap, type-token ratio, and genealogical distance emerge as top features across all architectures. Our findings reveal that a combination of typological and dataset-dependent features leads to the best rankings, and that good performance can be obtained with either feature group on its own.
Archival: Archival Track
Participation: In-person
Presenter: Enora Rice
Submission Number: 8
Loading