Overview for the Second Shared Task on Language Identification in\n Code-Switched Data

2019/09/27 by Giovanni Molina, Molina, Giovanni, Fahad AlGhamdi +11 · 4 citations
Social Sciences · Computer Science · #Multilingual Education and Policy #Digital Communication and Language

paper · pdf · doi:10.48550/arxiv.1909.13016

Abstract

We present an overview of the second shared task on language identification\nin code-switched data. For the shared task, we had code-switched data from two\ndifferent language pairs: Modern Standard Arabic-Dialectal Arabic (MSA-DA) and\nSpanish-English (SPA-ENG). We had a total of nine participating teams, with all\nteams submitting a system for SPA-ENG and four submitting for MSA-DA. Through\nevaluation, we found that once again language identification is more difficult\nfor the language pair that is more closely related. We also found that this\nyear's systems performed better overall than the systems from the previous\nshared task indicating overall progress in the state of the art for this task.\n

Cited by

• Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaraní
• Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models
• A Survey of Code-switched Speech and Language Processing
• CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages
• Char2Subword: Extending the Subword Embedding Space Using Robust\n Character Compositionality

Related

• CALCS 2021 Shared Task: Machine Translation for Code-Switched Data
• Computational Approaches to Arabic-English Code-Switching
• NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task
• Subword-Level Language Identification for Intra-Word Code-Switching
• Code-Switched Language Identification is Harder Than You Think