Cross-Lingual Transfer with Target Language-Ready Task Adapters

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A9BXK9XME" target="_blank" >RIV/00216208:11320/23:9BXK9XME - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175471784&partnerID=40&md5=3298fa4bb0804c28b68b479d16cd4a37" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175471784&partnerID=40&md5=3298fa4bb0804c28b68b479d16cd4a37</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Cross-Lingual Transfer with Target Language-Ready Task Adapters

Original language description

"Adapters have emerged as a modular and parameter-efficient approach to (zero-shot) cross-lingual transfer. The established MAD-X framework employs separate language and task adapters which can be arbitrarily combined to perform the transfer of any task to any target language. Subsequently, BAD-X, an extension of the MAD-X framework, achieves improved transfer at the cost of MAD-X's modularity by creating 'bilingual' adapters specific to the source-target language pair. In this work, we aim to take the best of both worlds by (i) fine-tuning task adapters adapted to the target language(s) (so-called 'target language-ready' (TLR) adapters) to maintain high transfer performance, but (ii) without sacrificing the highly modular design of MAD-X. The main idea of 'target language-ready' adapters is to resolve the training-vs-inference discrepancy of MAD-X: the task adapter 'sees' the target language adapter for the very first time during inference, and thus might not be fully compatible with it. We address this mismatch by exposing the task adapter to the target language adapter during training, and empirically validate several variants of the idea: in the simplest form, we alternate between using the source and target language adapters during task adapter training, which can be generalized to cycling over any set of language adapters. We evaluate different TLR-based transfer configurations with varying degrees of generality across a suite of standard cross-lingual benchmarks, and find that the most general (and thus most modular) configuration consistently outperforms MAD-X and BAD-X on most tasks and languages. © 2023 Association for Computational Linguistics."

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

2023

Confidentiality

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

Article name in the collection

"Proc. Annu. Meet. Assoc. Comput Linguist."

ISBN

978-195942962-3

ISSN

0736-587X

e-ISSN

—

Number of pages

18

Pages from-to

176-193

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

Melaka, Malaysia

Event date

Jan 1, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—