The Obscure Limitation of Modular Multilingual Language Models
Not on the map. Why?
Abstract (arXiv)
We expose the limitation of modular multilingual language models (MLMs) in multilingual inference scenarios with unknown languages. Existing evaluations of modular MLMs exclude the involvement of language identification (LID) modules, which obscures the performance of real-case multilingual scenarios of modular MLMs. In this work, we showcase the effect of adding LID on the multilingual evaluation of modular MLMs and provide discussions for closing the performance gap of caused by the pipelined approach of LID and modular MLMs.
Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 9 of its 17 references that are in the map. First posted on arXiv 21 Nov 2023.
Builds on
9 of 17 references.
References · 9
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,916
- 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,033
- 2016Bag of Tricks for Efficient Text Classificationcited by 872
- 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 741
- 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 443
- 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 145
- 2022Lifting the Curse of Multilinguality by Pre-training Modular Transformerscited by 145
- 2021IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generationcited by 57
- 2022IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languagescited by 42
Built on by
Citing papers per year: 2024: 3.
3 papers.