{"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/mt5","slug":"mt5","name":"mT5","full_name":"mT5","full_name_withheld":false,"description_markdown":"**mt5** is a multilingual variant of [T5](https://paperswithcode.com/method/t5) that was pre-trained on a new Common Crawl-based dataset covering $101$ languages.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2010.11934v3","title":"mT5: A massively multilingual pre-trained text-to-text transformer","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":104,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"advancing-sentiment-analysis-in-tamil-english","title":"Advancing Sentiment Analysis in Tamil-English Code-Mixed Texts: Challenges and Transformer-Based Solutions","date":"2025-03-30","arxiv_id":"2503.23295","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-robustness-of-multilingual-llms-on","slug":"exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-dialects-translating-standard-bangla","title":"Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models","date":"2025-01-10","arxiv_id":"2501.05749","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-bengali-education-with-ai-solving","title":"Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models","date":"2025-01-05","arxiv_id":"2501.02599","n_code_links":0,"syntology":null},{"paper":"/paper/belin-a-novel-corpus-for-bengali-religious","slug":"belin-a-novel-corpus-for-bengali-religious","title":"BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion","date":"2025-01-02","arxiv_id":"2501.01069","n_code_links":1,"syntology":null},{"paper":null,"slug":"hand-hierarchical-attention-network-for-multi","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","date":"2024-12-25","arxiv_id":"2412.18981","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-explainability-in-neural-machine","title":"Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency","date":"2024-12-24","arxiv_id":"2412.18669","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":"neural-text-normalization-for-luxembourgish","title":"Neural Text Normalization for Luxembourgish using Real-Life Variation Data","date":"2024-12-12","arxiv_id":"2412.09383","n_code_links":0,"syntology":null},{"paper":"/paper/sitse-sinhala-text-simplification-dataset-and","slug":"sitse-sinhala-text-simplification-dataset-and","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","date":"2024-12-02","arxiv_id":"2412.01293","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-santali-linguistic-inclusion-building","title":"Towards Santali Linguistic Inclusion: Building the First Santali-to-English Translation Model using mT5 Transformer and Data Augmentation","date":"2024-11-29","arxiv_id":"2411.19726","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-legal-knowledge-a-multilingual","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","date":"2024-10-17","arxiv_id":"2410.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-low-resourced","title":"Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers","date":"2024-09-29","arxiv_id":"2409.19566","n_code_links":0,"syntology":null},{"paper":"/paper/muri-high-quality-instruction-tuning-datasets","slug":"muri-high-quality-instruction-tuning-datasets","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","date":"2024-09-19","arxiv_id":"2409.12958","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-fine-tuned-generative-models-for","title":"Exploring Fine-tuned Generative Models for Keyphrase Selection: A Case Study for Russian","date":"2024-09-16","arxiv_id":"2409.10640","n_code_links":0,"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":"segment-based-interactive-machine-translation","title":"Segment-Based Interactive Machine Translation for Pre-trained Models","date":"2024-07-09","arxiv_id":"2407.06990","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-braille-an-end-to-end-tool-for-chinese","title":"Vision-Braille: An End-to-End Tool for Chinese Braille Image-to-Text Translation","date":"2024-07-08","arxiv_id":"2407.06048","n_code_links":0,"syntology":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/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":null,"slug":"transferring-troubles-cross-lingual","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","date":"2024-04-30","arxiv_id":"2404.19597","n_code_links":0,"syntology":null},{"paper":"/paper/indicgenbench-a-multilingual-benchmark-to","slug":"indicgenbench-a-multilingual-benchmark-to","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","date":"2024-04-25","arxiv_id":"2404.16816","n_code_links":1,"syntology":null},{"paper":null,"slug":"hltcoe-at-trec-2023-neuclir-track","title":"HLTCOE at TREC 2023 NeuCLIR Track","date":"2024-04-11","arxiv_id":"2404.08118","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-mt5-an-open-source-multilingual-text","title":"Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain","date":"2024-04-11","arxiv_id":"2404.07613","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/adaptive-cross-lingual-text-classification","slug":"adaptive-cross-lingual-text-classification","title":"Adaptive Cross-lingual Text Classification through In-Context One-Shot Demonstrations","date":"2024-04-03","arxiv_id":"2404.02452","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["villacu/ic_xlt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transcribing-bengali-text-with-regional","title":"Transcribing Bengali Text with Regional Dialects to IPA using District Guided Tokens","date":"2024-03-26","arxiv_id":"2403.17407","n_code_links":0,"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":null,"slug":"basque-and-spanish-counter-narrative","title":"Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation","date":"2024-03-14","arxiv_id":"2403.09159","n_code_links":0,"syntology":null},{"paper":null,"slug":"key-ingredients-for-effective-zero-shot-cross","title":"Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks","date":"2024-02-19","arxiv_id":"2402.12279","n_code_links":0,"syntology":null},{"paper":"/paper/inksight-offline-to-online-handwriting","slug":"inksight-offline-to-online-handwriting","title":"InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write","date":"2024-02-08","arxiv_id":"2402.05804","n_code_links":1,"syntology":null},{"paper":"/paper/topro-token-level-prompt-decomposition-for","slug":"topro-token-level-prompt-decomposition-for","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","date":"2024-01-29","arxiv_id":"2401.16589","n_code_links":1,"syntology":null},{"paper":"/paper/langbridge-multilingual-reasoning-without","slug":"langbridge-multilingual-reasoning-without","title":"LangBridge: Multilingual Reasoning Without Multilingual Supervision","date":"2024-01-19","arxiv_id":"2401.10695","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":3,"n_instrument":2,"unverified":7,"pointer_only":12,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["kaistAI/LangBridge"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/mapping-transformer-leveraged-embeddings-for","slug":"mapping-transformer-leveraged-embeddings-for","title":"Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation","date":"2024-01-12","arxiv_id":"2401.06583","n_code_links":1,"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":"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/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/famesumm-investigating-and-improving","slug":"famesumm-investigating-and-improving","title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","date":"2023-11-03","arxiv_id":"2311.02271","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["psunlpgroup/famesumm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/indo-lego-absa-a-multitask-generative-aspect","slug":"indo-lego-absa-a-multitask-generative-aspect","title":"Indo LEGO-ABSA: A Multitask Generative Aspect Based Sentiment Analysis for Indonesian Language","date":"2023-11-03","arxiv_id":"2311.01757","n_code_links":1,"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":"empirical-study-of-pretrained-multilingual","title":"Empirical study of pretrained multilingual language models for zero-shot cross-lingual knowledge transfer in generation","date":"2023-10-15","arxiv_id":"2310.09917","n_code_links":0,"syntology":null},{"paper":"/paper/capp-130-a-corpus-of-chinese-application","slug":"capp-130-a-corpus-of-chinese-application","title":"CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-procedural-language","slug":"benchmarking-procedural-language","title":"Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish","date":"2023-09-13","arxiv_id":"2309.06698","n_code_links":1,"syntology":null},{"paper":null,"slug":"mmt5-modular-multilingual-pre-training-solves","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","date":"2023-05-23","arxiv_id":"2305.14224","n_code_links":0,"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/mlongt5-a-multilingual-and-efficient-text-to","slug":"mlongt5-a-multilingual-and-efficient-text-to","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","date":"2023-05-18","arxiv_id":"2305.11129","n_code_links":1,"syntology":null},{"paper":"/paper/peach-pre-training-sequence-to-sequence","slug":"peach-pre-training-sequence-to-sequence","title":"PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation","date":"2023-04-03","arxiv_id":"2304.01282","n_code_links":1,"syntology":null},{"paper":null,"slug":"summarizing-indian-languages-using","title":"Summarizing Indian Languages using Multilingual Transformers based Models","date":"2023-03-29","arxiv_id":"2303.16657","n_code_links":0,"syntology":null},{"paper":"/paper/neuralmind-unicamp-at-2022-trec-neuclir-large","slug":"neuralmind-unicamp-at-2022-trec-neuclir-large","title":"NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval","date":"2023-03-28","arxiv_id":"2303.16145","n_code_links":1,"syntology":null},{"paper":"/paper/presto-a-multilingual-dataset-for-parsing","slug":"presto-a-multilingual-dataset-for-parsing","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","date":"2023-03-15","arxiv_id":"2303.08954","n_code_links":1,"syntology":null},{"paper":"/paper/are-character-level-translations-worth-the","slug":"are-character-level-translations-worth-the","title":"Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation","date":"2023-02-28","arxiv_id":"2302.14220","n_code_links":1,"syntology":null},{"paper":"/paper/vlsp-2022-evjvqa-challenge-multilingual","slug":"vlsp-2022-evjvqa-challenge-multilingual","title":"EVJVQA Challenge: Multilingual Visual Question Answering","date":"2023-02-23","arxiv_id":"2302.11752","n_code_links":0,"syntology":null},{"paper":null,"slug":"idt5-indonesian-version-of-multilingual-t5","title":"idT5: Indonesian Version of Multilingual T5 Transformer","date":"2023-02-02","arxiv_id":"2302.00856","n_code_links":0,"syntology":null},{"paper":"/paper/hunsum-1-an-abstractive-summarization-dataset","slug":"hunsum-1-an-abstractive-summarization-dataset","title":"HunSum-1: an Abstractive Summarization Dataset for Hungarian","date":"2023-02-01","arxiv_id":"2302.00455","n_code_links":1,"syntology":null},{"paper":"/paper/bipol-multi-axes-evaluation-of-bias-with","slug":"bipol-multi-axes-evaluation-of-bias-with","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","date":"2023-01-28","arxiv_id":"2301.12139","n_code_links":2,"syntology":null},{"paper":"/paper/bygpt5-end-to-end-style-conditioned-poetry","slug":"bygpt5-end-to-end-style-conditioned-poetry","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","date":"2022-12-20","arxiv_id":"2212.10474","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["potamides/uniformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mu-2-slam-multitask-multilingual-speech-and","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","date":"2022-12-19","arxiv_id":"2212.09553","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-sequence-to-sequence-models-for","title":"Multilingual Sequence-to-Sequence Models for Hebrew NLP","date":"2022-12-19","arxiv_id":"2212.09682","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-byte-and-wordpiece-level-models","title":"Evaluating Byte and Wordpiece Level Models for Massively Multilingual Semantic Parsing","date":"2022-12-14","arxiv_id":"2212.07223","n_code_links":0,"syntology":null},{"paper":"/paper/t5score-discriminative-fine-tuning-of","slug":"t5score-discriminative-fine-tuning-of","title":"T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics","date":"2022-12-12","arxiv_id":"2212.05726","n_code_links":2,"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":"/paper/glami-1m-a-multilingual-image-text-fashion-1","slug":"glami-1m-a-multilingual-image-text-fashion-1","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","date":"2022-11-17","arxiv_id":"2211.14451","n_code_links":1,"syntology":null},{"paper":"/paper/unified-question-answering-in-slovene","slug":"unified-question-answering-in-slovene","title":"Unified Question Answering in Slovene","date":"2022-11-16","arxiv_id":"2211.09159","n_code_links":1,"syntology":null},{"paper":"/paper/crosslingual-generalization-through-multitask","slug":"crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","arxiv_id":"2211.01786","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bigscience-workshop/xmtf"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"preserving-in-context-learning-ability-in","title":"Two-stage LLM Fine-tuning with Less Specialization and More Generalization","date":"2022-11-01","arxiv_id":"2211.00635","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-english-centric-bitexts-for-better","title":"Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning","date":"2022-10-26","arxiv_id":"2210.14867","n_code_links":0,"syntology":null},{"paper":"/paper/sling-sino-linguistic-evaluation-of-large","slug":"sling-sino-linguistic-evaluation-of-large","title":"SLING: Sino Linguistic Evaluation of Large Language Models","date":"2022-10-21","arxiv_id":"2210.11689","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["yixiao-song/sling_data_code"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tone-prediction-and-orthographic-conversion","title":"Tone prediction and orthographic conversion for Basaa","date":"2022-10-13","arxiv_id":"2210.06986","n_code_links":0,"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":"bidirectional-language-models-are-also-few","title":"Bidirectional Language Models Are Also Few-shot Learners","date":"2022-09-29","arxiv_id":"2209.14500","n_code_links":0,"syntology":null},{"paper":"/paper/xf2t-cross-lingual-fact-to-text-generation","slug":"xf2t-cross-lingual-fact-to-text-generation","title":"XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages","date":"2022-09-22","arxiv_id":"2209.11252","n_code_links":0,"syntology":null},{"paper":"/paper/mdia-a-benchmark-for-multilingual-dialogue","slug":"mdia-a-benchmark-for-multilingual-dialogue","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","date":"2022-08-27","arxiv_id":"2208.13078","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-boring-yet-effective-approach-for-the","title":"A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022","date":"2022-08-09","arxiv_id":"2208.06264","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-french-language-models-on","title":"Effectiveness of French Language Models on Abstractive Dialogue Summarization Task","date":"2022-07-17","arxiv_id":"2207.08305","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":"/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":"/paper/banglanlg-benchmarks-and-resources-for","slug":"banglanlg-benchmarks-and-resources-for","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","date":"2022-05-23","arxiv_id":"2205.11081","n_code_links":2,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish-1","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","date":"2022-05-18","arxiv_id":"2205.08808","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-arabic-sentence-simplification-via","title":"Towards Arabic Sentence Simplification via Classification and Generative Approaches","date":"2022-04-20","arxiv_id":"2204.09292","n_code_links":0,"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":null,"slug":"wordalchemy-a-transformer-based-reverse","title":"WordAlchemy: A transformer-based Reverse Dictionary","date":"2022-04-16","arxiv_id":"2204.10181","n_code_links":0,"syntology":null},{"paper":"/paper/byt5-model-for-massively-multilingual","slug":"byt5-model-for-massively-multilingual","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","date":"2022-04-06","arxiv_id":"2204.03067","n_code_links":1,"syntology":null},{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to-1","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-03-21","arxiv_id":"2203.10945","n_code_links":0,"syntology":null},{"paper":"/paper/coloring-the-blank-slate-pre-training-imparts-1","slug":"coloring-the-blank-slate-pre-training-imparts-1","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2022-03-17","arxiv_id":"2203.09397","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sebschu/multilingual-transformations"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"allwoz-towards-multilingual-task-oriented-1","title":"AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-pretrained-multilingual-models-equally","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-regressive-text-generation-with-pre","title":"Auto-regressive Text Generation with Pre-Trained Language Models: An Empirical Study on Question-type Short Text Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-low-resource-transfer-learning","title":"Exploring the Low-Resource Transfer-Learning with mT5 model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/crosssum-beyond-english-centric-cross-lingual","slug":"crosssum-beyond-english-centric-cross-lingual","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","date":"2021-12-16","arxiv_id":"2112.08804","n_code_links":1,"syntology":null},{"paper":null,"slug":"allwoz-towards-multilingual-task-oriented","title":"AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All","date":"2021-12-15","arxiv_id":"2112.08333","n_code_links":0,"syntology":null},{"paper":null,"slug":"coloring-the-blank-slate-pre-training-imparts","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"calculating-question-similarity-is-enough-a","title":"Calculating Question Similarity is Enough: A New Method for KBQA Tasks","date":"2021-11-15","arxiv_id":"2111.07658","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish","title":"Evaluation of Transfer Learning for Polish with a text-to-text model","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/arat5-text-to-text-transformers-for-arabic","slug":"arat5-text-to-text-transformers-for-arabic","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","date":"2021-08-31","arxiv_id":"2109.12068","n_code_links":1,"syntology":null},{"paper":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre-1","title":"nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/xl-sum-large-scale-multilingual-abstractive","slug":"xl-sum-large-scale-multilingual-abstractive","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","date":"2021-06-25","arxiv_id":"2106.13822","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["csebuetnlp/xl-sum"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/cpm-2-large-scale-cost-effective-pre-trained","slug":"cpm-2-large-scale-cost-effective-pre-trained","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","date":"2021-06-20","arxiv_id":"2106.10715","n_code_links":2,"syntology":null},{"paper":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre","title":"nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-06-03","arxiv_id":"2106.02171","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":104,"with_a_code_link":48,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":104,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/mt5/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/mt5/papers/2","json":"/method/mt5/papers/2.json","rows":4},{"order":"ran","page":1,"of":1,"url":"/method/mt5/papers/ran/1","json":"/method/mt5/papers/ran/1.json","rows":10}],"tasks":[{"task":"/task/translation","name":"Translation","papers":17},{"task":"/task/language-modelling","name":"Language Modelling","papers":16},{"task":"/task/machine-translation","name":"Machine Translation","papers":16},{"task":"/task/question-answering","name":"Question Answering","papers":14},{"task":"/task/language-modeling","name":"Language Modeling","papers":13},{"task":"/task/decoder","name":"Decoder","papers":12},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":11},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":11},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":9},{"task":"/task/xlm-r","name":"XLM-R","papers":9},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":8},{"task":"/task/sentence","name":"Sentence","papers":8},{"task":"/task/diversity","name":"Diversity","papers":7},{"task":"/task/denoising","name":"Denoising","papers":5},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":5},{"task":"/task/text-generation","name":"Text Generation","papers":5},{"task":"/task/text-summarization","name":"Text Summarization","papers":5},{"task":"/task/articles","name":"Articles","papers":4},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":4},{"task":"/task/multilingual-nlp","name":"Multilingual NLP","papers":4}],"tasks_shown":20,"n_tasks":133,"usage_by_year":[{"year":"2020","papers":2},{"year":"2021","papers":12},{"year":"2022","papers":34},{"year":"2023","papers":21},{"year":"2024","papers":30},{"year":"2025","papers":5}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mt5"},"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=mT5","read_at":"2026-10-05T00:59:22+00:00","query":"mT5","kind":"paper","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":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":2,"served":null,"leading_other_bearer":{"arxiv_id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","citations":3342,"named_by":["title_prefix"],"bearer_name":"mT5: A massively multilingual pre-trained text-to-text transformer","ask_with":"have('2010.11934')"},"n_other_bearers_listed":2,"note":"Nothing resolved to 'mT5' by name, but 2 thing(s) here DECLARE that name -- most cited: the paper 'mT5: A massively multilingual pre-trained text-to-text transformer' (arXiv:2010.11934, 3,342 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “mT5: A massively multilingual pre-trained text-to-text transformer” (arXiv:2010.11934, 3,342 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"e5e61ef2e8100daa5188bcb2b0c6934c50df03340533d14c734685e121d0a8e5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}