CALCS 2021 Shared Task: Machine Translation for Code-Switched Data

Abstract

To date, efforts in the code-switching literature have focused for the most part on language identification, POS, NER, and syntactic parsing. In this paper, we address machine translation for code-switched social media data. We create a community shared task. We provide two modalities for participation: supervised and unsupervised. For the supervised setting, participants are challenged to translate English into Hindi-English (Eng-Hinglish) in a single direction. For the unsupervised setting, we provide the following language pairs: English and Spanish-English (Eng-Spanglish), and English and Modern Standard Arabic-Egyptian Arabic (Eng-MSAEA) in both directions. We share insights and challenges in curating the "into" code-switching language evaluation data. Further, we provide baselines for all language pairs in the shared task. The leaderboard for the shared task comprises 12 individual system submissions corresponding to 5 different teams. The best performance achieved is 12.67% BLEU score for English to Hinglish and 25.72% BLEU score for MSAEA to English.

Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text

“…As for work on CS MT, there are many efforts (Sinha and Thakur, 2005;Dhar et al, 2018;Mahata et al, 2019;Menacer et al, 2019;Song et al, 2019;Tarunesh et al, 2021;Xu and Yvon, 2021;Chen et al, 2022;Hamed et al, 2022c). To the best of our knowledge, none of these efforts presented an extensive comparison covering different segmentation techniques.…”

“…We identify three main challenges for CS MT. First is data sparsity, a challenge common to many CS language pairs because of limited parallel corpora containing commissioned translations of CS text (Çetinoglu et al, 2016;Srivastava and Singh, 2020;Tarunesh et al, 2021;Hamed et al, 2022b;Chen et al, 2022). Second is Egyptian Arabic morphological richness, which further exacerbates the data sparsity situation (Habash et al, 2012a,b).…”

Detecting Propaganda Techniques in Code-Switched Social Media Text

“…Significant research efforts have been dedicated to various code-switched tasks in the field of Natural Language Processing (NLP), such as Language Identification, Named Entity Recognition (NER), POS Tagging, Sentiment Analysis, Question Answering, and Natural Language Inference (NLI) (Khanuja et al, 2020;Jose et al, 2020;Chen et al, 2022;Rizwan et al, 2020). However, there has been limited exploration in the domain of propaganda detection, particularly for low-resource languages.…”