MaskLID: Code-Switching Language Identification through Iterative Masking - Machine Learning and Information Access
Conference Papers Year : 2024

MaskLID: Code-Switching Language Identification through Iterative Masking

Abstract

We present MaskLID, a simple, yet effective, code-switching (CS) language identification (LID) method. MaskLID does not require any training and is designed to complement current high-performance sentence-level LIDs. Sentence-level LIDs are classifiers trained on monolingual texts to provide single labels, typically using a softmax layer to turn scores into probabilities. However, in cases where a sentence is composed in both L1 and L2 languages, the LID classifier often only returns the dominant label L1. To address this limitation, MaskLID employs a strategy to mask text features associated with L1, allowing the LID to classify the text as L2 in the next round. This method uses the LID itself to identify the features that require masking and does not rely on any external resource. In this work, we explore the use of MaskLID for two open-source LIDs (GlotLID and OpenLID), that are both based on the FastText architecture. Code and demo are available at https://github.com/cisnlp/MaskLID.
Fichier principal
Vignette du fichier
2024.acl-short.43.pdf (258.16 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-04670790 , version 1 (14-08-2024)

Licence

Identifiers

Cite

Amir Hossein Kargaran, François Yvon, Hinrich Schütze. MaskLID: Code-Switching Language Identification through Iterative Masking. 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Association for Computational Linguistics, Aug 2024, Bangkok, Thailand. pp.459-469. ⟨hal-04670790⟩
27 View
25 Download

Altmetric

Share

More