{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/xlm-r","slug":"xlm-r","name":"XLM-R","full_name":"XLM-R","full_name_withheld":false,"description_markdown":"XLM-R","description_state":"present","introduced_year":null,"introduced_by":{"title":"Unsupervised Cross-lingual Representation Learning at Scale","paper":"/paper/unsupervised-cross-lingual-representation-1","first_author":"Alexis Conneau","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/unsupervised-cross-lingual-representation-1"},"source":{"url":"https://arxiv.org/abs/1911.02116v2","title":"Unsupervised Cross-lingual Representation Learning at Scale","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":176,"archive_num_papers":176,"papers_newest_first":[{"paper":"/paper/multilingual-encoder-knows-more-than-you","slug":"multilingual-encoder-knows-more-than-you","title":"Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages","date":"2025-02-15","arxiv_id":"2502.10852","n_code_links":1,"syntology":null},{"paper":null,"slug":"amasquad-a-benchmark-for-amharic-extractive","title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering","date":"2025-02-04","arxiv_id":"2502.02047","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-xai","title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","date":"2025-01-26","arxiv_id":"2501.15374","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-approaches-to-sentiment-analysis","title":"Comparative Approaches to Sentiment Analysis Using Datasets in Major European and Arabic Languages","date":"2025-01-21","arxiv_id":"2501.12540","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-stage-training-of-bilingual-islamic-llm","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","date":"2025-01-17","arxiv_id":"2501.10175","n_code_links":0,"syntology":null},{"paper":null,"slug":"babylms-for-isixhosa-data-efficient-language","title":"BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context","date":"2025-01-07","arxiv_id":"2501.03855","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-applicability-of-zero-shot-cross","slug":"on-the-applicability-of-zero-shot-cross","title":"On the Applicability of Zero-Shot Cross-Lingual Transfer Learning for Sentiment Classification in Distant Language Pairs","date":"2024-12-24","arxiv_id":"2412.18188","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrofitting-large-language-models-with","title":"Retrofitting Large Language Models with Dynamic Tokenization","date":"2024-11-27","arxiv_id":"2411.18553","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-contextualized-language","title":"Transformer-Based Contextualized Language Models Joint with Neural Networks for Natural Language Inference in Vietnamese","date":"2024-11-20","arxiv_id":"2411.13407","n_code_links":0,"syntology":null},{"paper":"/paper/langsamp-language-script-aware-multilingual","slug":"langsamp-language-script-aware-multilingual","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","date":"2024-09-26","arxiv_id":"2409.18199","n_code_links":1,"syntology":null},{"paper":"/paper/lowrem-a-repository-of-word-embeddings-for-87","slug":"lowrem-a-repository-of-word-embeddings-for-87","title":"GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge","date":"2024-09-26","arxiv_id":"2409.18193","n_code_links":1,"syntology":null},{"paper":"/paper/mgte-generalized-long-context-text","slug":"mgte-generalized-long-context-text","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","date":"2024-07-29","arxiv_id":"2407.19669","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"the-model-arena-for-cross-lingual-sentiment","title":"The Model Arena for Cross-lingual Sentiment Analysis: A Comparative Study in the Era of Large Language Models","date":"2024-06-27","arxiv_id":"2406.19358","n_code_links":0,"syntology":null},{"paper":"/paper/medical-spoken-named-entity-recognition","slug":"medical-spoken-named-entity-recognition","title":"Medical Spoken Named Entity Recognition","date":"2024-06-19","arxiv_id":"2406.13337","n_code_links":1,"syntology":null},{"paper":null,"slug":"targeted-multilingual-adaptation-for-low","title":"Targeted Multilingual Adaptation for Low-resource Language Families","date":"2024-05-20","arxiv_id":"2405.12413","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-mental-health-prediction-tasks-for","title":"Adapting Mental Health Prediction Tasks for Cross-lingual Learning via Meta-Training and In-context Learning with Large Language Model","date":"2024-04-13","arxiv_id":"2404.09045","n_code_links":0,"syntology":null},{"paper":null,"slug":"mainlp-at-semeval-2024-task-1-analyzing","title":"MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness","date":"2024-04-03","arxiv_id":"2404.02570","n_code_links":0,"syntology":null},{"paper":"/paper/cicle-conformal-in-context-learning-for","slug":"cicle-conformal-in-context-learning-for","title":"CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification","date":"2024-03-18","arxiv_id":"2403.11904","n_code_links":1,"syntology":null},{"paper":null,"slug":"machines-do-see-color-a-guideline-to-classify","title":"Machines Do See Color: A Guideline to Classify Different Forms of Racist Discourse in Large Corpora","date":"2024-01-17","arxiv_id":"2401.09333","n_code_links":0,"syntology":null},{"paper":null,"slug":"lingualchemy-fusing-typological-and","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","date":"2024-01-11","arxiv_id":"2401.06034","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-content-detection","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","date":"2023-12-09","arxiv_id":"2312.05671","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-text-to-text-model-for-multilingual","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","n_code_links":0,"syntology":null},{"paper":"/paper/kbioxlm-a-knowledge-anchored-biomedical","slug":"kbioxlm-a-knowledge-anchored-biomedical","title":"KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model","date":"2023-11-20","arxiv_id":"2311.11564","n_code_links":1,"syntology":null},{"paper":"/paper/mela-multilingual-evaluation-of-linguistic","slug":"mela-multilingual-evaluation-of-linguistic","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","date":"2023-11-15","arxiv_id":"2311.09033","n_code_links":1,"syntology":null},{"paper":"/paper/calamancy-a-tagalog-natural-language","slug":"calamancy-a-tagalog-natural-language","title":"calamanCy: A Tagalog Natural Language Processing Toolkit","date":"2023-11-13","arxiv_id":"2311.07171","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-cross-lingual-sentiment","title":"Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study","date":"2023-11-11","arxiv_id":"2311.06549","n_code_links":0,"syntology":null},{"paper":"/paper/improving-cross-lingual-transfer-through","slug":"improving-cross-lingual-transfer-through","title":"Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering","date":"2023-10-20","arxiv_id":"2310.13583","n_code_links":1,"syntology":null},{"paper":null,"slug":"medai-dialog-corpus-medic-zero-shot","title":"MedAI Dialog Corpus (MEDIC): Zero-Shot Classification of Doctor and AI Responses in Health Consultations","date":"2023-10-19","arxiv_id":"2310.12489","n_code_links":0,"syntology":null},{"paper":"/paper/visobert-a-pre-trained-language-model-for","slug":"visobert-a-pre-trained-language-model-for","title":"ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing","date":"2023-10-17","arxiv_id":"2310.11166","n_code_links":1,"syntology":null},{"paper":"/paper/qasina-religious-domain-question-answering","slug":"qasina-religious-domain-question-answering","title":"QASiNa: Religious Domain Question Answering using Sirah Nabawiyah","date":"2023-10-12","arxiv_id":"2310.08102","n_code_links":1,"syntology":null},{"paper":"/paper/mbbc-exploring-the-multilingual-maze","slug":"mbbc-exploring-the-multilingual-maze","title":"Exploring the Maze of Multilingual Modeling","date":"2023-10-09","arxiv_id":"2310.05404","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixed-distil-bert-code-mixed-language","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","date":"2023-09-19","arxiv_id":"2309.10272","n_code_links":0,"syntology":null},{"paper":"/paper/differential-privacy-linguistic-fairness-and","slug":"differential-privacy-linguistic-fairness-and","title":"Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models","date":"2023-08-17","arxiv_id":"2308.08774","n_code_links":0,"syntology":{"ran":14,"of":23,"n_ran_checked":14,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":null}},{"paper":null,"slug":"does-mbert-understand-romansh-evaluating-word","title":"Does mBERT understand Romansh? Evaluating word embeddings using word alignment","date":"2023-06-14","arxiv_id":"2306.08702","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-relationship-between-alignment","slug":"exploring-the-relationship-between-alignment","title":"Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers","date":"2023-06-05","arxiv_id":"2306.02790","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["posos-tech/multilingual-alignment-and-transfer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/distilling-efficient-language-specific-models","slug":"distilling-efficient-language-specific-models","title":"Distilling Efficient Language-Specific Models for Cross-Lingual Transfer","date":"2023-06-02","arxiv_id":"2306.01709","n_code_links":1,"syntology":null},{"paper":"/paper/focus-effective-embedding-initialization-for","slug":"focus-effective-embedding-initialization-for","title":"FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models","date":"2023-05-23","arxiv_id":"2305.14481","n_code_links":2,"syntology":null},{"paper":"/paper/towards-massively-multi-domain-multilingual","slug":"towards-massively-multi-domain-multilingual","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","date":"2023-05-23","arxiv_id":"2305.14463","n_code_links":1,"syntology":null},{"paper":"/paper/dumb-a-benchmark-for-smart-evaluation-of","slug":"dumb-a-benchmark-for-smart-evaluation-of","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","date":"2023-05-22","arxiv_id":"2305.13026","n_code_links":2,"syntology":null},{"paper":null,"slug":"extrapolating-multilingual-understanding","title":"Extrapolating Multilingual Understanding Models as Multilingual Generators","date":"2023-05-22","arxiv_id":"2305.13140","n_code_links":0,"syntology":null},{"paper":"/paper/escoxlm-r-multilingual-taxonomy-driven-pre","slug":"escoxlm-r-multilingual-taxonomy-driven-pre","title":"ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain","date":"2023-05-20","arxiv_id":"2305.12092","n_code_links":1,"syntology":null},{"paper":"/paper/glot500-scaling-multilingual-corpora-and","slug":"glot500-scaling-multilingual-corpora-and","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","date":"2023-05-20","arxiv_id":"2305.12182","n_code_links":1,"syntology":null},{"paper":null,"slug":"dn-at-semeval-2023-task-12-low-resource","title":"DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning","date":"2023-05-04","arxiv_id":"2305.02607","n_code_links":0,"syntology":null},{"paper":null,"slug":"ustc-nelslip-at-semeval-2023-task-2","title":"USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER","date":"2023-05-04","arxiv_id":"2305.02517","n_code_links":0,"syntology":null},{"paper":"/paper/greekbart-the-first-pretrained-greek-sequence","slug":"greekbart-the-first-pretrained-greek-sequence","title":"GreekBART: The First Pretrained Greek Sequence-to-Sequence Model","date":"2023-04-03","arxiv_id":"2304.00869","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-the-effectiveness-of-pre-trained","slug":"evaluating-the-effectiveness-of-pre-trained","title":"Evaluating the Effectiveness of Pre-trained Language Models in Predicting the Helpfulness of Online Product Reviews","date":"2023-02-19","arxiv_id":"2302.10199","n_code_links":1,"syntology":null},{"paper":"/paper/modeling-sequential-sentence-relation-to","slug":"modeling-sequential-sentence-relation-to","title":"Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval","date":"2023-02-03","arxiv_id":"2302.01626","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-sentence-transformer-as-a","slug":"multilingual-sentence-transformer-as-a","title":"Multilingual Sentence Transformer as A Multilingual Word Aligner","date":"2023-01-28","arxiv_id":"2301.12140","n_code_links":1,"syntology":null},{"paper":"/paper/xlm-v-overcoming-the-vocabulary-bottleneck-in","slug":"xlm-v-overcoming-the-vocabulary-bottleneck-in","title":"XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models","date":"2023-01-25","arxiv_id":"2301.10472","n_code_links":3,"syntology":null},{"paper":null,"slug":"integrating-semantic-information-into-sketchy","title":"Integrating Semantic Information into Sketchy Reading Module of Retro-Reader for Vietnamese Machine Reading Comprehension","date":"2023-01-01","arxiv_id":"2301.00429","n_code_links":0,"syntology":null},{"paper":"/paper/damp-doubly-aligned-multilingual-parser-for","slug":"damp-doubly-aligned-multilingual-parser-for","title":"DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue","date":"2022-12-15","arxiv_id":"2212.08054","n_code_links":1,"syntology":null},{"paper":"/paper/indicxtreme-a-multi-task-benchmark-for","slug":"indicxtreme-a-multi-task-benchmark-for","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","date":"2022-12-11","arxiv_id":"2212.05409","n_code_links":1,"syntology":null},{"paper":"/paper/punctuation-restoration-for-singaporean","slug":"punctuation-restoration-for-singaporean","title":"Punctuation Restoration for Singaporean Spoken Languages: English, Malay, and Mandarin","date":"2022-12-10","arxiv_id":"2212.05356","n_code_links":1,"syntology":null},{"paper":null,"slug":"languages-you-know-influence-those-you-learn","title":"Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer","date":"2022-12-04","arxiv_id":"2212.01757","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-cross-lingual-multi-task-models","title":"Compressing Cross-Lingual Multi-Task Models at Qualtrics","date":"2022-11-29","arxiv_id":"2211.15927","n_code_links":0,"syntology":null},{"paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"l3cube-hindbert-and-devbert-pre-trained-bert","title":"L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages","date":"2022-11-21","arxiv_id":"2211.11418","n_code_links":0,"syntology":null},{"paper":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","n_code_links":2,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/collateral-facilitation-in-humans-and","slug":"collateral-facilitation-in-humans-and","title":"Collateral facilitation in humans and language models","date":"2022-11-09","arxiv_id":"2211.05198","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jmichaelov/collateral-facilitation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/iitd-at-the-wanlp-2022-shared-task","slug":"iitd-at-the-wanlp-2022-shared-task","title":"IITD at the WANLP 2022 Shared Task: Multilingual Multi-Granularity Network for Propaganda Detection","date":"2022-10-31","arxiv_id":"2210.17190","n_code_links":1,"syntology":null},{"paper":"/paper/improving-bilingual-lexicon-induction-with-1","slug":"improving-bilingual-lexicon-induction-with-1","title":"Improving Bilingual Lexicon Induction with Cross-Encoder Reranking","date":"2022-10-30","arxiv_id":"2210.16953","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cambridgeltl/BLICEr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-simple-and-effective-method-to-improve-zero-1","slug":"a-simple-and-effective-method-to-improve-zero-1","title":"A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning","date":"2022-10-18","arxiv_id":"2210.09934","n_code_links":1,"syntology":null},{"paper":"/paper/alibaba-translate-china-s-submission-for-wmt-1","slug":"alibaba-translate-china-s-submission-for-wmt-1","title":"Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task","date":"2022-10-18","arxiv_id":"2210.10049","n_code_links":1,"syntology":null},{"paper":"/paper/are-pretrained-multilingual-models-equally-1","slug":"are-pretrained-multilingual-models-equally-1","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-10-11","arxiv_id":"2210.05457","n_code_links":1,"syntology":null},{"paper":"/paper/disfluency-detection-for-vietnamese","slug":"disfluency-detection-for-vietnamese","title":"Disfluency Detection for Vietnamese","date":"2022-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/how-about-time-probing-a-multilingual","slug":"how-about-time-probing-a-multilingual","title":"How about Time? Probing a Multilingual Language Model for Temporal Relations","date":"2022-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"extending-word-level-quality-estimation-for","title":"Extending Word-Level Quality Estimation for Post-Editing Assistance","date":"2022-09-23","arxiv_id":"2209.11378","n_code_links":0,"syntology":null},{"paper":null,"slug":"smtce-a-social-media-text-classification","title":"SMTCE: A Social Media Text Classification Evaluation Benchmark and BERTology Models for Vietnamese","date":"2022-09-21","arxiv_id":"2209.10482","n_code_links":0,"syntology":null},{"paper":null,"slug":"alexsis-pt-a-new-resource-for-portuguese","title":"ALEXSIS-PT: A New Resource for Portuguese Lexical Simplification","date":"2022-09-19","arxiv_id":"2209.09034","n_code_links":0,"syntology":null},{"paper":"/paper/from-disfluency-detection-to-intent-detection","slug":"from-disfluency-detection-to-intent-detection","title":"From Disfluency Detection to Intent Detection and Slot Filling","date":"2022-09-17","arxiv_id":"2209.08359","n_code_links":1,"syntology":null},{"paper":"/paper/multi-stage-distillation-framework-for-cross-2","slug":"multi-stage-distillation-framework-for-cross-2","title":"Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching","date":"2022-09-13","arxiv_id":"2209.05869","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-bidirectional-unsupervised","slug":"multilingual-bidirectional-unsupervised","title":"Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation","date":"2022-09-06","arxiv_id":"2209.02821","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-colbert-x","slug":"multilingual-colbert-x","title":"Neural Approaches to Multilingual Information Retrieval","date":"2022-09-03","arxiv_id":"2209.01335","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-language-relationships-in","title":"Investigating Language Relationships in Multilingual Sentence Encoders Through the Lens of Linguistic Typology","date":"2022-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bertifying-sinhala-a-comprehensive-analysis","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","date":"2022-08-16","arxiv_id":"2208.07864","n_code_links":0,"syntology":null},{"paper":null,"slug":"asner-annotated-dataset-and-baseline-for","title":"AsNER -- Annotated Dataset and Baseline for Assamese Named Entity recognition","date":"2022-07-07","arxiv_id":"2207.03422","n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2022-task-2-on-the","title":"Hitachi at SemEval-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection","date":"2022-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sliced-at-semeval-2022-task-11-bigger-better","title":"Sliced at SemEval-2022 Task 11: Bigger, Better? Massively Multilingual LMs for Multilingual Complex NER on an Academic GPU Budget","date":"2022-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alexa-teacher-model-pretraining-and","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","date":"2022-06-15","arxiv_id":"2206.07808","n_code_links":0,"syntology":null},{"paper":null,"slug":"asner-annotated-dataset-and-baseline-for-1","title":"AsNER - Annotated Dataset and Baseline for Assamese Named Entity recognition","date":"2022-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bertifying-sinhala-a-comprehensive-analysis-1","slug":"bertifying-sinhala-a-comprehensive-analysis-1","title":"BERTifying Sinhala - A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"debating-europe-a-multilingual-multi-target","title":"Debating Europe: A Multilingual Multi-Target Stance Classification Dataset of Online Debates","date":"2022-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-mono-and-cross-lingual","title":"Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models","date":"2022-05-24","arxiv_id":"2205.11758","n_code_links":0,"syntology":null},{"paper":"/paper/the-geometry-of-multilingual-language-model","slug":"the-geometry-of-multilingual-language-model","title":"The Geometry of Multilingual Language Model Representations","date":"2022-05-22","arxiv_id":"2205.10964","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-text-classification-using-graph","slug":"multi-task-text-classification-using-graph","title":"Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Language","date":"2022-05-02","arxiv_id":"2205.01204","n_code_links":1,"syntology":null},{"paper":null,"slug":"black-lscdiscovery-shared-task-glossreader-at","title":"black[LSCDiscovery shared task] GlossReader at LSCDiscovery: Train to Select a Proper Gloss in English – Discover Lexical Semantic Change in Spanish","date":"2022-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cuet-nlp-tamilnlp-acl2022-multi-class-textual","title":"CUET-NLP@TamilNLP-ACL2022: Multi-Class Textual Emotion Detection from Social Media using Transformer","date":"2022-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/explaining-classes-through-stable-word","slug":"explaining-classes-through-stable-word","title":"Explaining Classes through Stable Word Attributions","date":"2022-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"teluguner-leveraging-multi-domain-named","title":"TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers","date":"2022-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-making-the-most-of-cross-lingual","slug":"towards-making-the-most-of-cross-lingual","title":"Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation","date":"2022-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/massive-a-1m-example-multilingual-natural","slug":"massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","arxiv_id":"2204.08582","n_code_links":6,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alexa/massive"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/the-impact-of-cross-lingual-adjustment-of-1","slug":"the-impact-of-cross-lingual-adjustment-of-1","title":"The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer","date":"2022-04-13","arxiv_id":"2204.06457","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-not-fire-the-linguist-grammatical-profiles","title":"Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change","date":"2022-04-12","arxiv_id":"2204.05717","n_code_links":0,"syntology":null},{"paper":"/paper/factual-consistency-of-multilingual","slug":"factual-consistency-of-multilingual","title":"Factual Consistency of Multilingual Pretrained Language Models","date":"2022-03-22","arxiv_id":"2203.11552","n_code_links":1,"syntology":null},{"paper":"/paper/towards-explainable-evaluation-metrics-for","slug":"towards-explainable-evaluation-metrics-for","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","date":"2022-03-21","arxiv_id":"2203.11131","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-multilingual-language-models-capture","title":"Do Multilingual Language Models Capture Differing Moral Norms?","date":"2022-03-18","arxiv_id":"2203.09904","n_code_links":0,"syntology":null},{"paper":"/paper/combining-static-and-contextualised-1","slug":"combining-static-and-contextualised-1","title":"Combining Static and Contextualised Multilingual Embeddings","date":"2022-03-17","arxiv_id":"2203.09326","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-ability-of-multilingual-masked","title":"Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure","date":"2022-03-16","arxiv_id":"2203.08430","n_code_links":0,"syntology":null},{"paper":"/paper/overlap-based-vocabulary-generation-improves","slug":"overlap-based-vocabulary-generation-improves","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","date":"2022-03-03","arxiv_id":"2203.01976","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vaidehi99/obpe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/transfer-learning-approaches-for-building","slug":"transfer-learning-approaches-for-building","title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","date":"2022-01-20","arxiv_id":"2201.08471","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hltcoe/colbert-x"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":176,"with_a_code_link":80,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":176,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/method/xlm-r/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/xlm-r/papers/2","json":"/method/xlm-r/papers/2.json","rows":76},{"order":"ran","page":1,"of":1,"url":"/method/xlm-r/papers/ran/1","json":"/method/xlm-r/papers/ran/1.json","rows":14}],"tasks":[{"task":"/task/xlm-r","name":"XLM-R","papers":174},{"task":"/task/language-modelling","name":"Language Modelling","papers":40},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":34},{"task":"/task/language-modeling","name":"Language Modeling","papers":31},{"task":"/task/sentence","name":"Sentence","papers":25},{"task":"/task/text-classification","name":"Text Classification","papers":17},{"task":"/task/text-classification-1","name":"text-classification","papers":17},{"task":"/task/cg","name":"NER","papers":16},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":14},{"task":"/task/zero-shot-cross-lingual-transfer","name":"Zero-Shot Cross-Lingual Transfer","papers":14},{"task":"/task/classification-1","name":"Classification","papers":13},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":13},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":13},{"task":"/task/named-entity-recognition","name":"named-entity-recognition","papers":13},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":12},{"task":"/task/question-answering","name":"Question Answering","papers":11},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":11},{"task":"/task/machine-translation","name":"Machine Translation","papers":10},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":10},{"task":"/task/retrieval","name":"Retrieval","papers":10}],"tasks_shown":20,"n_tasks":179,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":18},{"year":"2021","papers":52},{"year":"2022","papers":55},{"year":"2023","papers":30},{"year":"2024","papers":14},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/xlm-r"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=XLM-R","read_at":"2026-10-05T01:04:00+00:00","query":"XLM-R","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"XLM-R","origin_arxiv_id":"1911.02116"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"1911.02116","repositories":{"listed":5,"in_graph":35,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1911.02116","citations":9089},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'XLM-R'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"1911.02116","page":"/paper/unsupervised-cross-lingual-representation-1","syntology_url":"https://syntology.ai/paper/1911.02116","in_graph_layer":true,"samples":59,"ran":40,"n_ran_checked":35,"n_instrument":5,"unverified":19,"phrase":"40 ran (of which 13 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 35 in the graph, strongest link: official). This answer is about arXiv:1911.02116, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"d17f9422dc067927b8485c2a351dcd5164519dc4a4cafab2c9a273a5c4748255","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}