{"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/xlm-t-a-multilingual-language-model-toolkit","title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","arxiv_id":"2104.12250","date":"2021-04-25","proceeding":"LREC 2022 6","authors":["Francesco Barbieri","Luis Espinosa Anke","Jose Camacho-Collados"],"abstract":"Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter. In this paper we provide: (1) a new strong multilingual baseline consisting of an XLM-R (Conneau et al. 2020) model pre-trained on millions of tweets in over thirty languages, alongside starter code to subsequently fine-tune on a target task; and (2) a set of unified sentiment analysis Twitter datasets in eight different languages and a XLM-T model fine-tuned on them.","url_abs":"https://arxiv.org/abs/2104.12250v2","url_pdf":"https://arxiv.org/pdf/2104.12250v2.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":"xlm-t-a-multilingual-language-model-toolkit","repo_url":"https://github.com/cardiffnlp/xlm-t","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"xlm-r","task_name":"XLM-R"}],"methods":[{"method_slug":"xlm-r","method_name":"XLM-R"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-tweeteval","task":"Sentiment Analysis","dataset":"TweetEval","model":"RoB-RT","rank_in_archive_order":2,"of":7,"metrics":{"ALL":"65.2","Emoji":"31.4","Emotion":"79.5","Hate":"52.3","Irony":"61.7","Offensive":"80.5","Sentiment":"72.6","Stance":"69.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.12250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12250"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cardiffnlp/xlm-t","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c0eb04b8ef584d55","entry":"all_languages_results","repo":"cardiffnlp/xlm-t","repo_kind":"official","path":"src/evaluation_script.py","file_url":"https://github.com/cardiffnlp/xlm-t/blob/HEAD/src/evaluation_script.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c0eb04b8ef584d55"}},{"code_sha256_prefix":"1e359fdd4a264166","entry":"load_gold_pred","repo":"cardiffnlp/xlm-t","repo_kind":"official","path":"src/evaluation_script.py","file_url":"https://github.com/cardiffnlp/xlm-t/blob/HEAD/src/evaluation_script.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e359fdd4a264166"}},{"code_sha256_prefix":"f6c8e77eefa080a6","entry":"single_language_result","repo":"cardiffnlp/xlm-t","repo_kind":"official","path":"src/evaluation_script.py","file_url":"https://github.com/cardiffnlp/xlm-t/blob/HEAD/src/evaluation_script.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6c8e77eefa080a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}