The Impact of Language Adapters in Cross-Lingual Transfer for NLU

Jenny Kunz, Oskar Holmström
1/31/2024
cs.CL

No official code found. Best implementation: oskarholmstrom/lang-adapters-impact (3 stars, last commit 2024-01-26).

Abstract

Modular deep learning has been proposed for the efficient adaption of pre-trained models to new tasks, domains and languages. In particular, combining language adapters with task adapters has shown potential where no supervised data exists for a language. In this paper, we explore the role of language adapters in zero-shot cross-lingual transfer for natural language understanding (NLU) benchmarks. We study the effect of including a target-language adapter in detailed ablation studies with two multilingual models and three multilingual datasets. Our results show that the effect of target-language adapters is highly inconsistent across tasks, languages and models. Retaining the source-language adapter instead often leads to an equivalent, and sometimes to a better, performance. Removing the language adapter after training has only a weak negative effect, indicating that the language adapters do not have a strong impact on the predictions.

View on arXivView PDF

Code Implementations(1)

oskarholmstrom/lang-adapters-impactCommunity100%
30Shell, PythonJan 26, 20242 years ago

Similar Papers

An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models

87% match2024

Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks

87% match2024

No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement

87% match1 repo12024

Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models

87% match2024

Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Transfer in Sense-Aware Tasks

86% match2025

What Causes Knowledge Loss in Multilingual Language Models?

86% match2025

Cite this paper

@article{kunz2024impact,
  title  = {The Impact of Language Adapters in Cross-Lingual Transfer for NLU},
  author = {Jenny Kunz and Oskar Holmström},
  year   = {2024},
  eprint = {2402.00149},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.00149v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.00149.svg)](https://codeofpaper.com/paper/2402.00149)

Discussion