Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages

Verena Blaschke, Hinrich Schütze, Barbara Plank


Abstract
One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for instance be observed when finetuning PLMs on one language and evaluating them on data in a closely related language variety with no standardized orthography. Despite the high linguistic similarity, tokenization no longer corresponds to meaningful representations of the target data, leading to low performance in, e.g., part-of-speech tagging. In this work, we finetune PLMs on seven languages from three different families and analyze their zero-shot performance on closely related, non-standardized varieties. We consider different measures for the divergence in the tokenization of the source and target data, and the way they can be adjusted by manipulating the tokenization during the finetuning step. Overall, we find that the similarity between the percentage of words that get split into subwords in the source and target data (the split word ratio difference) is the strongest predictor for model performance on target data.
Anthology ID:
2023.vardial-1.5
Volume:
Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Yves Scherrer, Tommi Jauhiainen, Nikola Ljubešić, Preslav Nakov, Jörg Tiedemann, Marcos Zampieri
Venue:
VarDial
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–54
Language:
URL:
https://aclanthology.org/2023.vardial-1.5
DOI:
10.18653/v1/2023.vardial-1.5
Bibkey:
Cite (ACL):
Verena Blaschke, Hinrich Schütze, and Barbara Plank. 2023. Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages. In Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023), pages 40–54, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages (Blaschke et al., VarDial 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.vardial-1.5.pdf
Video:
 https://aclanthology.org/2023.vardial-1.5.mp4