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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AVDT78TGQ" target="_blank" >RIV/00216208:11320/23:VDT78TGQ - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175993250&partnerID=40&md5=ecffab857a150327e8de9df245757f47" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175993250&partnerID=40&md5=ecffab857a150327e8de9df245757f47</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

"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. © 2023 Association for Computational Linguistics."

Název v anglickém jazyce

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

Popis výsledku anglicky

"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. © 2023 Association for Computational Linguistics."

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

"ACL - Workshop NLP Similar Lang., Var. Dialects, VarDial - Proc. Workshop"

ISBN

978-195942950-0

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

40-54

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Melaka, Malaysia

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—