Adapting Monolingual Models: Data can be Scarce when Language Similarity is High

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440894" target="_blank" >RIV/00216208:11320/21:10440894 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Adapting Monolingual Models: Data can be Scarce when Language Similarity is High

Original language description

For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as possible, and the influence of language similarity in this process. We retrain the lexical layers of four BERT-based models using data from two low-resource target language varieties, while the Transformer layers are independently fine-tuned on a POS-tagging task in the model&apos;s source language. By combining the new lexical layers and fine-tuned Transformer layers, we achieve high task performance for both target languages. With high language similarity, 10MB of data appears sufficient to achieve substantial monolingual transfer performance. Monolingual BERT-based models generally achieve higher downstream task performance after retraining the lexical layer than multilingual BERT, even when the target language is included in the multilingual model.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2021

Confidentiality

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

Article name in the collection

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

ISBN

978-1-954085-54-1

ISSN

—

e-ISSN

—

Number of pages

7

Pages from-to

4901-4907

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg

Event location

online

Event date

Aug 1, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—