Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917968067166208 |
|---|---|
| author | Rice, Enora Marashian, Ali Haynie, Hannah von der Wense, Katharina Palmer, Alexis |
| author_facet | Rice, Enora Marashian, Ali Haynie, Hannah von der Wense, Katharina Palmer, Alexis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19979 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging Rice, Enora Marashian, Ali Haynie, Hannah von der Wense, Katharina Palmer, Alexis Computation and Language 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. |
| title | Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.19979 |