{"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/mbert","slug":"mbert","name":"mBERT","full_name":"mBERT","full_name_withheld":false,"description_markdown":"mBERT","description_state":"present","introduced_year":null,"introduced_by":{"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","paper":"/paper/bert-pre-training-of-deep-bidirectional","first_author":"Jacob Devlin","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/bert-pre-training-of-deep-bidirectional"},"source":{"url":"https://arxiv.org/abs/1810.04805v2","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","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":198,"archive_num_papers":198,"papers_newest_first":[{"paper":null,"slug":"how-do-datasets-developers-and-models-affect","title":"How do datasets, developers, and models affect biases in a low-resourced language?","date":"2025-06-07","arxiv_id":"2506.06816","n_code_links":0,"syntology":null},{"paper":null,"slug":"university-of-indonesia-at-semeval-2025-task","title":"University of Indonesia at SemEval-2025 Task 11: Evaluating State-of-the-Art Encoders for Multi-Label Emotion Detection","date":"2025-05-22","arxiv_id":"2505.16460","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-linguistic-transfer-in-multilingual-nlp","title":"Cross-Linguistic Transfer in Multilingual NLP: The Role of Language Families and Morphology","date":"2025-05-20","arxiv_id":"2505.13908","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-synthetic-oracle-datasets-to","title":"Generating Synthetic Oracle Datasets to Analyze Noise Impact: A Study on Building Function Classification Using Tweets","date":"2025-03-28","arxiv_id":"2503.22856","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":"the-first-multilingual-model-for-the","title":"The First Multilingual Model For The Detection of Suicide Texts","date":"2024-12-20","arxiv_id":"2412.15498","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/from-n-grams-to-pre-trained-multilingual","slug":"from-n-grams-to-pre-trained-multilingual","title":"From N-grams to Pre-trained Multilingual Models For Language Identification","date":"2024-10-11","arxiv_id":"2410.08728","n_code_links":2,"syntology":null},{"paper":"/paper/motamot-a-dataset-for-revealing-the-supremacy","slug":"motamot-a-dataset-for-revealing-the-supremacy","title":"Motamot: A Dataset for Revealing the Supremacy of Large Language Models over Transformer Models in Bengali Political Sentiment Analysis","date":"2024-07-28","arxiv_id":"2407.19528","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-initializing-transformers-with-pre-trained","title":"On Initializing Transformers with Pre-trained Embeddings","date":"2024-07-17","arxiv_id":"2407.12514","n_code_links":0,"syntology":null},{"paper":null,"slug":"decipherment-aware-multilingual-learning-in","title":"Decipherment-Aware Multilingual Learning in Jointly Trained Language Models","date":"2024-06-11","arxiv_id":"2406.07231","n_code_links":0,"syntology":null},{"paper":null,"slug":"vietnamese-ai-generated-text-detection","title":"Vietnamese AI Generated Text Detection","date":"2024-05-06","arxiv_id":"2405.03206","n_code_links":0,"syntology":null},{"paper":"/paper/unraveling-the-dominance-of-large-language","slug":"unraveling-the-dominance-of-large-language","title":"Unraveling the Dominance of Large Language Models Over Transformer Models for Bangla Natural Language Inference: A Comprehensive Study","date":"2024-05-05","arxiv_id":"2405.02937","n_code_links":1,"syntology":null},{"paper":"/paper/uqa-corpus-for-urdu-question-answering","slug":"uqa-corpus-for-urdu-question-answering","title":"UQA: Corpus for Urdu Question Answering","date":"2024-05-02","arxiv_id":"2405.01458","n_code_links":3,"syntology":null},{"paper":"/paper/incorporating-lexical-and-syntactic-knowledge","slug":"incorporating-lexical-and-syntactic-knowledge","title":"Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer","date":"2024-04-25","arxiv_id":"2404.16627","n_code_links":1,"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":"/paper/data-bias-according-to-bipol-men-are","slug":"data-bias-according-to-bipol-men-are","title":"Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead","date":"2024-04-07","arxiv_id":"2404.04838","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-for-expansion-of-spoken","slug":"large-language-models-for-expansion-of-spoken","title":"Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages","date":"2024-04-03","arxiv_id":"2404.02588","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-benchmark-evaluation-of-clinical-named","title":"A Benchmark Evaluation of Clinical Named Entity Recognition in French","date":"2024-03-28","arxiv_id":"2403.19726","n_code_links":0,"syntology":null},{"paper":null,"slug":"introducing-syllable-tokenization-for-low","title":"Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahili","date":"2024-03-26","arxiv_id":"2406.15358","n_code_links":0,"syntology":null},{"paper":"/paper/ax-to-grind-urdu-benchmark-dataset-for-urdu","slug":"ax-to-grind-urdu-benchmark-dataset-for-urdu","title":"Ax-to-Grind Urdu: Benchmark Dataset for Urdu Fake News Detection","date":"2024-03-20","arxiv_id":"2403.14037","n_code_links":1,"syntology":null},{"paper":"/paper/llmlingua-2-data-distillation-for-efficient","slug":"llmlingua-2-data-distillation-for-efficient","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","date":"2024-03-19","arxiv_id":"2403.12968","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","n_code_links":2,"syntology":null},{"paper":"/paper/a-measure-for-transparent-comparison-of","slug":"a-measure-for-transparent-comparison-of","title":"A Measure for Transparent Comparison of Linguistic Diversity in Multilingual NLP Data Sets","date":"2024-03-06","arxiv_id":"2403.03909","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-esg-impact-type-identification","title":"Enhancing ESG Impact Type Identification through Early Fusion and Multilingual Models","date":"2024-02-16","arxiv_id":"2402.10772","n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-editing-in-multilingual","slug":"cross-lingual-editing-in-multilingual","title":"Cross-lingual Editing in Multilingual Language Models","date":"2024-01-19","arxiv_id":"2401.10521","n_code_links":1,"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":"/paper/multilingual-large-language-models-leak-human","slug":"multilingual-large-language-models-leak-human","title":"Multilingual large language models leak human stereotypes across language boundaries","date":"2023-12-12","arxiv_id":"2312.07141","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-significance-of-subword-tokenization-for","title":"On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi","date":"2023-12-03","arxiv_id":"2312.01306","n_code_links":0,"syntology":null},{"paper":"/paper/vashantor-a-large-scale-multilingual","slug":"vashantor-a-large-scale-multilingual","title":"Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language","date":"2023-11-18","arxiv_id":"2311.11142","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/investigating-bias-in-multilingual-language","slug":"investigating-bias-in-multilingual-language","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","date":"2023-10-16","arxiv_id":"2310.10310","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":"/paper/tackling-fake-news-in-bengali-unraveling-the","slug":"tackling-fake-news-in-bengali-unraveling-the","title":"Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models","date":"2023-07-13","arxiv_id":"2307.06979","n_code_links":1,"syntology":null},{"paper":"/paper/ai-upv-at-exist-2023-sexism-characterization","slug":"ai-upv-at-exist-2023-sexism-characterization","title":"AI-UPV at EXIST 2023 -- Sexism Characterization Using Large Language Models Under The Learning with Disagreements Regime","date":"2023-07-07","arxiv_id":"2307.03385","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-multiword-expression","title":"Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation","date":"2023-06-17","arxiv_id":"2306.10419","n_code_links":0,"syntology":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/dlama-a-framework-for-curating-culturally","slug":"dlama-a-framework-for-curating-culturally","title":"DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models","date":"2023-06-08","arxiv_id":"2306.05076","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-technical-report-for-polyglot-ko-open","title":"A Technical Report for Polyglot-Ko: Open-Source Large-Scale Korean Language Models","date":"2023-06-04","arxiv_id":"2306.02254","n_code_links":0,"syntology":null},{"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":null,"slug":"feed-pets-further-experimentation-and","title":"FEED PETs: Further Experimentation and Expansion on the Disambiguation of Potentially Euphemistic Terms","date":"2023-05-31","arxiv_id":"2306.00217","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-study-of-pre-trained-bert-models","title":"Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data","date":"2023-05-25","arxiv_id":"2305.15722","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-linguistic-generalisation-in","title":"Assessing Linguistic Generalisation in Language Models: A Dataset for Brazilian Portuguese","date":"2023-05-23","arxiv_id":"2305.14070","n_code_links":0,"syntology":null},{"paper":"/paper/llm-powered-data-augmentation-for-enhanced","slug":"llm-powered-data-augmentation-for-enhanced","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","date":"2023-05-23","arxiv_id":"2305.14288","n_code_links":1,"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/natural-language-processing-and-sentiment","slug":"natural-language-processing-and-sentiment","title":"Natural Language Processing and Sentiment Analysis on Bangla Social Media Comments on Russia–Ukraine War Using Transformers","date":"2023-05-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-bert-and-parsbert-for-analyzing","title":"evaluating bert and parsbert for analyzing persian advertisement data","date":"2023-05-03","arxiv_id":"2305.02426","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-to-a-low-resource-language-via-close","title":"Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese","date":"2023-04-18","arxiv_id":"2304.08823","n_code_links":0,"syntology":null},{"paper":"/paper/team-sheffieldveraai-at-semeval-2023-task-3","slug":"team-sheffieldveraai-at-semeval-2023-task-3","title":"SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification","date":"2023-03-16","arxiv_id":"2303.09421","n_code_links":1,"syntology":null},{"paper":"/paper/the-impact-of-subword-pooling-strategy-for","slug":"the-impact-of-subword-pooling-strategy-for","title":"Impact of Subword Pooling Strategy on Cross-lingual Event Detection","date":"2023-02-22","arxiv_id":"2302.11365","n_code_links":1,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-language-detection-2","title":"Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder","date":"2023-02-17","arxiv_id":"2302.08777","n_code_links":0,"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":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/microbert-effective-training-of-low-resource","slug":"microbert-effective-training-of-low-resource","title":"MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning","date":"2022-12-23","arxiv_id":"2212.12510","n_code_links":1,"syntology":null},{"paper":null,"slug":"camembert-cascading-assistant-mediated","title":"CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT","date":"2022-12-22","arxiv_id":"2212.11456","n_code_links":0,"syntology":null},{"paper":"/paper/cross-linguistic-syntactic-difference-in","slug":"cross-linguistic-syntactic-difference-in","title":"Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?","date":"2022-12-21","arxiv_id":"2212.10879","n_code_links":1,"syntology":null},{"paper":"/paper/naamapadam-a-large-scale-named-entity","slug":"naamapadam-a-large-scale-named-entity","title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages","date":"2022-12-20","arxiv_id":"2212.10168","n_code_links":1,"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/patient-friendly-clinical-notes-towards-a-new","slug":"patient-friendly-clinical-notes-towards-a-new","title":"Patient-friendly Clinical Notes: Towards a new Text Simplification Dataset","date":"2022-12-07","arxiv_id":null,"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":null,"slug":"intriguing-properties-of-compression-on","title":"Intriguing Properties of Compression on Multilingual Models","date":"2022-11-04","arxiv_id":"2211.02738","n_code_links":0,"syntology":null},{"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/universal-and-independent-multilingual","slug":"universal-and-independent-multilingual","title":"Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation","date":"2022-10-24","arxiv_id":"2210.13236","n_code_links":2,"syntology":null},{"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/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":null,"slug":"better-than-whitespace-information-retrieval","title":"Better Than Whitespace: Information Retrieval for Languages without Custom Tokenizers","date":"2022-10-11","arxiv_id":"2210.05481","n_code_links":0,"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":"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":null,"slug":"babelbert-massively-multilingual-transformers","title":"Massively Multilingual Lexical Specialization of Multilingual Transformers","date":"2022-08-01","arxiv_id":"2208.01018","n_code_links":0,"syntology":null},{"paper":"/paper/integrating-linguistic-theory-and-neural","slug":"integrating-linguistic-theory-and-neural","title":"Integrating Linguistic Theory and Neural Language Models","date":"2022-07-20","arxiv_id":"2207.09643","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-transformers-for-product","title":"Multilingual Transformers for Product Matching -- Experiments and a New Benchmark in Polish","date":"2022-05-31","arxiv_id":"2205.15712","n_code_links":0,"syntology":null},{"paper":"/paper/discovering-language-neutral-sub-networks-in","slug":"discovering-language-neutral-sub-networks-in","title":"Discovering Language-neutral Sub-networks in Multilingual Language Models","date":"2022-05-25","arxiv_id":"2205.12672","n_code_links":1,"syntology":null},{"paper":"/paper/geomlama-geo-diverse-commonsense-probing-on","slug":"geomlama-geo-diverse-commonsense-probing-on","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","date":"2022-05-24","arxiv_id":"2205.12247","n_code_links":1,"syntology":null},{"paper":null,"slug":"sample-efficient-approaches-for-idiomaticity","title":"Sample Efficient Approaches for Idiomaticity Detection","date":"2022-05-23","arxiv_id":"2205.11306","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-data-quality-and-quantity-for-a","slug":"pre-training-data-quality-and-quantity-for-a","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","date":"2022-05-21","arxiv_id":"2205.10517","n_code_links":1,"syntology":null},{"paper":"/paper/persian-natural-language-inference-a-meta-1","slug":"persian-natural-language-inference-a-meta-1","title":"Persian Natural Language Inference: A Meta-learning approach","date":"2022-05-18","arxiv_id":"2205.08755","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-aggregation-in-zero-shot-cross","title":"Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT","date":"2022-05-17","arxiv_id":"2205.08497","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-static-models-and-test-sets-1","title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages","date":"2022-05-12","arxiv_id":"2205.06356","n_code_links":0,"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":"/paper/yosm-a-new-yoruba-sentiment-corpus-for-movie","slug":"yosm-a-new-yoruba-sentiment-corpus-for-movie","title":"yosm: A new yoruba sentiment corpus for movie reviews","date":"2022-04-20","arxiv_id":"2204.09711","n_code_links":1,"syntology":null},{"paper":null,"slug":"mono-vs-multilingual-bert-for-hate-speech","title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi","date":"2022-04-19","arxiv_id":"2204.08669","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-benchmarks-for-spanish-sentence","slug":"evaluation-benchmarks-for-spanish-sentence","title":"Evaluation Benchmarks for Spanish Sentence Representations","date":"2022-04-15","arxiv_id":"2204.07571","n_code_links":1,"syntology":null},{"paper":"/paper/latent-aspect-detection-from-online","slug":"latent-aspect-detection-from-online","title":"Latent Aspect Detection from Online Unsolicited Customer Reviews","date":"2022-04-14","arxiv_id":"2204.06964","n_code_links":1,"syntology":null},{"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":"/paper/l3cube-mahaner-a-marathi-named-entity","slug":"l3cube-mahaner-a-marathi-named-entity","title":"L3Cube-MahaNER: A Marathi Named Entity Recognition Dataset and BERT models","date":"2022-04-12","arxiv_id":"2204.06029","n_code_links":1,"syntology":null},{"paper":"/paper/mucot-multilingual-contrastive-training-for","slug":"mucot-multilingual-contrastive-training-for","title":"MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages","date":"2022-04-12","arxiv_id":"2204.05814","n_code_links":1,"syntology":null},{"paper":"/paper/learning-disentangled-semantic","slug":"learning-disentangled-semantic","title":"Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension","date":"2022-04-03","arxiv_id":"2204.00996","n_code_links":1,"syntology":null},{"paper":"/paper/bitsa-nlp-lt-edi-acl2022-leveraging","slug":"bitsa-nlp-lt-edi-acl2022-leveraging","title":"bitsa_nlp@LT-EDI-ACL2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media Comments","date":"2022-03-27","arxiv_id":"2203.14267","n_code_links":1,"syntology":null},{"paper":"/paper/l3cube-mahahate-a-tweet-based-marathi-hate","slug":"l3cube-mahahate-a-tweet-based-marathi-hate","title":"L3Cube-MahaHate: A Tweet-based Marathi Hate Speech Detection Dataset and BERT models","date":"2022-03-25","arxiv_id":"2203.13778","n_code_links":1,"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":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/zero-shot-dependency-parsing-with-worst-case-1","slug":"zero-shot-dependency-parsing-with-worst-case-1","title":"Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning","date":"2022-03-16","arxiv_id":"2203.08555","n_code_links":1,"syntology":null},{"paper":"/paper/improving-word-translation-via-two-stage-1","slug":"improving-word-translation-via-two-stage-1","title":"Improving Word Translation via Two-Stage Contrastive Learning","date":"2022-03-15","arxiv_id":"2203.08307","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cambridgeltl/contrastivebli"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"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"]}}}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":198,"with_a_code_link":98,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":198,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":10,"papers_where_code_ran_first_page":"/method/mbert/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/mbert/papers/2","json":"/method/mbert/papers/2.json","rows":98},{"order":"ran","page":1,"of":1,"url":"/method/mbert/papers/ran/1","json":"/method/mbert/papers/ran/1.json","rows":10}],"tasks":[{"task":"/task/xlm-r","name":"XLM-R","papers":49},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":40},{"task":"/task/language-modelling","name":"Language Modelling","papers":29},{"task":"/task/zero-shot-cross-lingual-transfer","name":"Zero-Shot Cross-Lingual Transfer","papers":23},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":22},{"task":"/task/language-modeling","name":"Language Modeling","papers":20},{"task":"/task/cg","name":"NER","papers":19},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":19},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":19},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":18},{"task":"/task/sentence","name":"Sentence","papers":18},{"task":"/task/named-entity-recognition","name":"named-entity-recognition","papers":16},{"task":"/task/pos","name":"POS","papers":15},{"task":"/task/pos-tagging","name":"POS Tagging","papers":13},{"task":"/task/text-classification","name":"Text Classification","papers":13},{"task":"/task/translation","name":"Translation","papers":12},{"task":"/task/word-embeddings","name":"Word Embeddings","papers":12},{"task":"/task/text-classification-1","name":"text-classification","papers":12},{"task":"/task/dependency-parsing","name":"Dependency Parsing","papers":11},{"task":"/task/machine-translation","name":"Machine Translation","papers":11}],"tasks_shown":20,"n_tasks":170,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":34},{"year":"2021","papers":56},{"year":"2022","papers":47},{"year":"2023","papers":31},{"year":"2024","papers":22},{"year":"2025","papers":5}],"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/mbert"},"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=mBERT","read_at":"2026-10-05T00:58:59+00:00","query":"mBERT","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1810.04805","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'mBERT' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["E-MBERT"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"7dcd80954c1fe81995ba50cb3eb9096735c1a0ff56e1c3dab51a429ab98f83f0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}