Back to Search Start Over

A cost-benefit analysis of cross-lingual transfer methods

Authors :
Rosa, Guilherme Moraes
Bonifacio, Luiz Henrique
de Souza, Leandro Rodrigues
Lotufo, Roberto
Nogueira, Rodrigo
Publication Year :
2021
Publisher :
arXiv, 2021.

Abstract

An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate that the best cross-lingual method is highly task-dependent. Finally, by combining zero-shot and translation methods, we achieve the state-of-the-art in two of the three datasets used in this work. Based on these results, we question the need for manually labeled training data in a target language. Code and translated datasets are available at https://github.com/unicamp-dl/cross-lingual-analysis

Details

Database :
OpenAIRE
Accession number :
edsair.doi.dedup.....9b97e14dc53838856f6057b159526e02
Full Text :
https://doi.org/10.48550/arxiv.2105.06813