{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/improved-multilingual-language-model","title":"Improved Multilingual Language Model Pretraining for Social Media Text via Translation Pair Prediction","arxiv_id":"2110.10318","date":"2021-10-20","proceeding":"WNUT (ACL) 2021 11","authors":["Shubhanshu Mishra","Aria Haghighi"],"abstract":"We evaluate a simple approach to improving zero-shot multilingual transfer of mBERT on social media corpus by adding a pretraining task called translation pair prediction (TPP), which predicts whether a pair of cross-lingual texts are a valid translation. Our approach assumes access to translations (exact or approximate) between source-target language pairs, where we fine-tune a model on source language task data and evaluate the model in the target language. In particular, we focus on language pairs where transfer learning is difficult for mBERT: those where source and target languages are different in script, vocabulary, and linguistic typology. We show improvements from TPP pretraining over mBERT alone in zero-shot transfer from English to Hindi, Arabic, and Japanese on two social media tasks: NER (a 37% average relative improvement in F1 across target languages) and sentiment classification (12% relative improvement in F1) on social media text, while also benchmarking on a non-social media task of Universal Dependency POS tagging (6.7% relative improvement in accuracy). Our results are promising given the lack of social media bitext corpus. Our code can be found at: https://github.com/twitter-research/multilingual-alignment-tpp.","url_abs":"https://arxiv.org/abs/2110.10318v1","url_pdf":"https://arxiv.org/pdf/2110.10318v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"improved-multilingual-language-model","repo_url":"https://github.com/twitter-research/multilingual-alignment-tpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"mbert","method_name":"mBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.10318","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}