{"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":"/task/multilingual-nlp","name":"Multilingual NLP","slug":"multilingual-nlp","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":96,"papers_with_code":42,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68},{"url":"/dataset/duolingo-staple-shared-task","name":"Duolingo STAPLE Shared Task","full_name":"","num_papers_in_archive":10},{"url":"/dataset/humset","name":"HumSet","full_name":"HumSet","num_papers_in_archive":2},{"url":"/dataset/m2qa","name":"M2QA","full_name":"Multi-domain Multilingual Question Answering","num_papers_in_archive":2},{"url":"/dataset/glare","name":"GLARE","full_name":"Guided LexRank for Advanced Retrieval in Legal Analysis","num_papers_in_archive":1},{"url":"/dataset/maked","name":"MAKED","full_name":"MultiModal MultiLingual Summarization and Keyword Extraction Dataset","num_papers_in_archive":1},{"url":"/dataset/mbbc","name":"mBBC dataset","full_name":"Multilingual BBC news","num_papers_in_archive":1},{"url":"/dataset/english-pashto-language-dataset-epld","name":"English-Pashto Language Dataset (EPLD)","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":96,"of":96,"of_with_code":42,"tagged_in_all":96,"counts":{"archive_papers_tagged":96,"with_a_code_link":42,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":96,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"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"},"items":[{"url":"/paper/unsupervised-cross-lingual-representation-1","slug":"unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","arxiv_id":"1911.02116","repositories_listed":35,"syntology":{"n":59,"n_ran":40,"n_constructed":13,"n_ran_checked":35,"n_instrument":5,"n_unverified":19,"n_honours":4,"n_violates":1,"n_no_contract":30,"n_pointer_only":52,"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","sample_list":"/paper/unsupervised-cross-lingual-representation-1#ran","syntology_url":"https://syntology.ai/paper/1911.02116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02116"}},"official":{"repos":["facebookresearch/cc_net","facebookresearch/XLM"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/bloom-a-176b-parameter-open-access","slug":"bloom-a-176b-parameter-open-access","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","date":"2022-11-09","arxiv_id":"2211.05100","repositories_listed":7,"syntology":{"n":11,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/bloom-a-176b-parameter-open-access#ran","syntology_url":"https://syntology.ai/paper/2211.05100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05100"}},"official":null}},{"url":"/paper/language-agnostic-bert-sentence-embedding","slug":"language-agnostic-bert-sentence-embedding","title":"Language-agnostic BERT Sentence Embedding","date":"2020-07-03","arxiv_id":"2007.01852","repositories_listed":6,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/paper/what-is-typological-diversity-in-nlp","slug":"what-is-typological-diversity-in-nlp","title":"What is \"Typological Diversity\" in NLP?","date":"2024-02-06","arxiv_id":"2402.04222","repositories_listed":2,"syntology":null},{"url":"/paper/crosslingual-transfer-learning-for-low","slug":"crosslingual-transfer-learning-for-low","title":"Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs","date":"2023-05-22","arxiv_id":"2305.12818","repositories_listed":2,"syntology":null},{"url":"/paper/xeroalign-zero-shot-cross-lingual-transformer","slug":"xeroalign-zero-shot-cross-lingual-transformer","title":"XeroAlign: Zero-Shot Cross-lingual Transformer Alignment","date":"2021-05-06","arxiv_id":"2105.02472","repositories_listed":2,"syntology":null},{"url":"/paper/pmindia-a-collection-of-parallel-corpora-of","slug":"pmindia-a-collection-of-parallel-corpora-of","title":"PMIndia -- A Collection of Parallel Corpora of Languages of India","date":"2020-01-27","arxiv_id":"2001.09907","repositories_listed":2,"syntology":null},{"url":"/paper/mmcr4nlp-multilingual-multiway-corpora","slug":"mmcr4nlp-multilingual-multiway-corpora","title":"MMCR4NLP: Multilingual Multiway Corpora Repository for Natural Language Processing","date":"2017-10-03","arxiv_id":"1710.01025","repositories_listed":2,"syntology":null},{"url":"/paper/news-without-borders-domain-adaptation-of","slug":"news-without-borders-domain-adaptation-of","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","date":"2024-06-18","arxiv_id":"2406.12634","repositories_listed":1,"syntology":null},{"url":"/paper/proxylm-predicting-language-model-performance","slug":"proxylm-predicting-language-model-performance","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","date":"2024-06-13","arxiv_id":"2406.09334","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/proxylm-predicting-language-model-performance#ran","syntology_url":"https://syntology.ai/paper/2406.09334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09334"}},"official":{"repos":["davidanugraha/proxylm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-language-bias-between-french-and","slug":"analyzing-language-bias-between-french-and","title":"Analyzing Language Bias Between French and English in Conventional Multilingual Sentiment Analysis Models","date":"2024-05-07","arxiv_id":"2405.06692","repositories_listed":1,"syntology":null},{"url":"/paper/what-drives-performance-in-multilingual","slug":"what-drives-performance-in-multilingual","title":"What Drives Performance in Multilingual Language Models?","date":"2024-04-29","arxiv_id":"2404.19159","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/self-augmented-in-context-learning-for","slug":"self-augmented-in-context-learning-for","title":"Self-Augmented In-Context Learning for Unsupervised Word Translation","date":"2024-02-15","arxiv_id":"2402.10024","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-augmented-in-context-learning-for#ran","syntology_url":"https://syntology.ai/paper/2402.10024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10024"}},"official":{"repos":["cambridgeltl/sail-bli"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-bilingual-lexicon-induction-with-large","slug":"on-bilingual-lexicon-induction-with-large","title":"On Bilingual Lexicon Induction with Large Language Models","date":"2023-10-21","arxiv_id":"2310.13995","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-bilingual-lexicon-induction-with-large#ran","syntology_url":"https://syntology.ai/paper/2310.13995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13995"}},"official":{"repos":["cambridgeltl/prompt4bli"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/baitbuster-bangla-a-comprehensive-dataset-for","slug":"baitbuster-bangla-a-comprehensive-dataset-for","title":"BaitBuster-Bangla: A Comprehensive Dataset for Clickbait Detection in Bangla with Multi-Feature and Multi-Modal Analysis","date":"2023-10-13","arxiv_id":"2310.11465","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-effectiveness-of-capsule","slug":"evaluating-the-effectiveness-of-capsule","title":"Evaluating The Effectiveness of Capsule Neural Network in Toxic Comment Classification using Pre-trained BERT Embeddings","date":"2023-10-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/monolingual-or-multilingual-instruction","slug":"monolingual-or-multilingual-instruction","title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","date":"2023-09-16","arxiv_id":"2309.08958","repositories_listed":1,"syntology":null},{"url":"/paper/xtreme-up-a-user-centric-scarce-data","slug":"xtreme-up-a-user-centric-scarce-data","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","date":"2023-05-19","arxiv_id":"2305.11938","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/xtreme-up-a-user-centric-scarce-data#ran","syntology_url":"https://syntology.ai/paper/2305.11938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11938"}},"official":{"repos":["google-research/xtreme-up"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pmindiasum-multilingual-and-cross-lingual","slug":"pmindiasum-multilingual-and-cross-lingual","title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","date":"2023-05-15","arxiv_id":"2305.08828","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-purpose-multilingual-document","slug":"a-general-purpose-multilingual-document","title":"A General-Purpose Multilingual Document Encoder","date":"2023-05-11","arxiv_id":"2305.07016","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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","sample_list":"/paper/improving-bilingual-lexicon-induction-with-1#ran","syntology_url":"https://syntology.ai/paper/2210.16953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16953"}},"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"]}}},{"url":"/paper/humset-dataset-of-multilingual-information","slug":"humset-dataset-of-multilingual-information","title":"HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response","date":"2022-10-10","arxiv_id":"2210.04573","repositories_listed":1,"syntology":null},{"url":"/paper/detie-multilingual-open-information","slug":"detie-multilingual-open-information","title":"DetIE: Multilingual Open Information Extraction Inspired by Object Detection","date":"2022-06-24","arxiv_id":"2206.12514","repositories_listed":1,"syntology":null},{"url":"/paper/teddi-sample-text-data-diversity-sample-for","slug":"teddi-sample-text-data-diversity-sample-for","title":"TeDDi Sample: Text Data Diversity Sample for Language Comparison and Multilingual NLP","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/improving-word-translation-via-two-stage-1#ran","syntology_url":"https://syntology.ai/paper/2203.08307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08307"}},"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"]}}},{"url":"/paper/improving-word-translation-via-two-stage","slug":"improving-word-translation-via-two-stage","title":"Improving Word Translation via Two-Stage Contrastive Learning","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/wikineural-combined-neural-and-knowledge","slug":"wikineural-combined-neural-and-knowledge","title":"WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cultural-and-geographical-influences-on-image","slug":"cultural-and-geographical-influences-on-image","title":"Cultural and Geographical Influences on Image Translatability of Words across Languages","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/honest-measuring-hurtful-sentence-completion","slug":"honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/analysing-the-impact-of-linguistic-features","slug":"analysing-the-impact-of-linguistic-features","title":"Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer","date":"2021-05-12","arxiv_id":"2105.05975","repositories_listed":1,"syntology":null},{"url":"/paper/samanantar-the-largest-publicly-available","slug":"samanantar-the-largest-publicly-available","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","date":"2021-04-12","arxiv_id":"2104.05596","repositories_listed":1,"syntology":null},{"url":"/paper/sick-nl-a-dataset-for-dutch-natural-language","slug":"sick-nl-a-dataset-for-dutch-natural-language","title":"SICK-NL: A Dataset for Dutch Natural Language Inference","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sicknl-a-dataset-for-dutch-natural-language","slug":"sicknl-a-dataset-for-dutch-natural-language","title":"SICKNL: A Dataset for Dutch Natural Language Inference","date":"2021-01-14","arxiv_id":"2101.05716","repositories_listed":1,"syntology":null},{"url":"/paper/trankit-a-light-weight-transformer-based","slug":"trankit-a-light-weight-transformer-based","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","date":"2021-01-09","arxiv_id":"2101.03289","repositories_listed":1,"syntology":null},{"url":"/paper/manual-clustering-and-spatial-arrangement-of","slug":"manual-clustering-and-spatial-arrangement-of","title":"Manual Clustering and Spatial Arrangement of Verbs for Multilingual Evaluation and Typology Analysis","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fugashi-a-tool-for-tokenizing-japanese-in","slug":"fugashi-a-tool-for-tokenizing-japanese-in","title":"fugashi, a Tool for Tokenizing Japanese in Python","date":"2020-10-14","arxiv_id":"2010.06858","repositories_listed":1,"syntology":null},{"url":"/paper/simultaneous-translation-and-paraphrase-for","slug":"simultaneous-translation-and-paraphrase-for","title":"Simultaneous Translation and Paraphrase for Language Education","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sequence-tagging-with-contextual-and-non","slug":"sequence-tagging-with-contextual-and-non","title":"Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation","date":"2019-06-04","arxiv_id":"1906.01569","repositories_listed":1,"syntology":null},{"url":"/paper/improving-cross-lingual-word-embeddings-by","slug":"improving-cross-lingual-word-embeddings-by","title":"Improving Cross-Lingual Word Embeddings by Meeting in the Middle","date":"2018-08-27","arxiv_id":"1808.08780","repositories_listed":1,"syntology":null},{"url":null,"slug":"multilinguality-does-not-make-sense","title":"Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Transfer in Sense-Aware Tasks","date":"2025-05-30","arxiv_id":"2505.24834","repositories_listed":0,"syntology":null},{"url":null,"slug":"senwich-sense-annotation-of-low-resource","title":"SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods","date":"2025-05-29","arxiv_id":"2505.23714","repositories_listed":0,"syntology":null},{"url":null,"slug":"lago-few-shot-crosslingual-embedding","title":"LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization","date":"2025-05-21","arxiv_id":"2505.16008","repositories_listed":0,"syntology":null},{"url":null,"slug":"shared-path-unraveling-memorization-in","title":"Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities","date":"2025-05-21","arxiv_id":"2505.15722","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"hausanlp-current-status-challenges-and-future","title":"HausaNLP: Current Status, Challenges and Future Directions for Hausa Natural Language Processing","date":"2025-05-20","arxiv_id":"2505.14311","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-prompt-engineering-in-large","title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","date":"2025-05-16","arxiv_id":"2505.11665","repositories_listed":0,"syntology":null},{"url":null,"slug":"bias-beyond-english-evaluating-social-bias","title":"Bias Beyond English: Evaluating Social Bias and Debiasing Methods in a Low-Resource Setting","date":"2025-04-15","arxiv_id":"2504.11183","repositories_listed":0,"syntology":null},{"url":"/paper/poly-fever-a-multilingual-fact-verification","slug":"poly-fever-a-multilingual-fact-verification","title":"Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models","date":"2025-03-19","arxiv_id":"2503.16541","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-mixed-telugu-english-hate-speech","title":"Code-Mixed Telugu-English Hate Speech Detection","date":"2025-02-15","arxiv_id":"2502.10632","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-a-multilingual-lm-handle-multiple","title":"How does a Multilingual LM Handle Multiple Languages?","date":"2025-02-06","arxiv_id":"2502.04269","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-good-is-your-wikipedia","title":"How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP","date":"2024-11-08","arxiv_id":"2411.05527","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-touch-my-diacritics","title":"Don't Touch My Diacritics","date":"2024-10-31","arxiv_id":"2410.24140","repositories_listed":0,"syntology":null},{"url":null,"slug":"sandboxaq-s-submission-to-mrl-2024-shared","title":"SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval","date":"2024-10-28","arxiv_id":"2410.21501","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-llms-to-hebrew-unveiling-dictalm-2-0","title":"Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities","date":"2024-07-09","arxiv_id":"2407.07080","repositories_listed":0,"syntology":null},{"url":null,"slug":"dravidian-language-family-through-universal","title":"Dravidian language family through Universal Dependencies lens","date":"2024-06-20","arxiv_id":"2406.14680","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-evaluation-practices-in-multilingual","title":"On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?","date":"2024-06-20","arxiv_id":"2406.14267","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-to-measure","title":"Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora","date":"2024-06-19","arxiv_id":"2406.13677","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-pre-trained-large-language","title":"Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks","date":"2024-05-24","arxiv_id":"2405.15453","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reproducibility-study-on-quantifying","title":"A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base","date":"2024-05-17","arxiv_id":"2405.11125","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-translation-all-you-need-a-study-on","title":"Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models","date":"2024-03-15","arxiv_id":"2403.10258","repositories_listed":0,"syntology":null},{"url":null,"slug":"patterns-of-persistence-and-diffusibility","title":"Patterns of Persistence and Diffusibility across the World's Languages","date":"2024-01-03","arxiv_id":"2401.01698","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-word-embeddings-for-low-resource","title":"Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages","date":"2023-11-21","arxiv_id":"2311.12489","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-teacher-distillation-for-multilingual","title":"Multi-teacher Distillation for Multilingual Spelling Correction","date":"2023-11-20","arxiv_id":"2311.11518","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-study-of-performance-disparities","title":"A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems","date":"2023-10-19","arxiv_id":"2310.12892","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-cross-lingual-transfer-without","title":"Zero-shot Cross-lingual Transfer without Parallel Corpus","date":"2023-10-07","arxiv_id":"2310.04726","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-augmentation-improves-zero-shot-cross","title":"Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer","date":"2023-09-19","arxiv_id":"2309.10891","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-beyond-english-towards-a","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","date":"2023-04-12","arxiv_id":"2304.05613","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-multilingual-encoders-learn-cross","title":"How Do Multilingual Encoders Learn Cross-lingual Representation?","date":"2022-07-12","arxiv_id":"2207.05737","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-strategies-in-cross-cultural","title":"Challenges and Strategies in Cross-Cultural NLP","date":"2022-03-18","arxiv_id":"2203.10020","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-performance-of-multilingual","title":"Predicting the Performance of Multilingual NLP Models","date":"2021-10-17","arxiv_id":"2110.08875","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-in-representation-for-multilingual","title":"Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-representation-sprachbund-for","title":"Discovering Representation Sprachbund For Multilingual Pre-Training","date":"2021-09-01","arxiv_id":"2109.00271","repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parcoure-a-parallel-corpus-explorer-fora","title":"ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus","date":"2021-07-14","arxiv_id":"2107.06632","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-considerations-with-code-mixed","title":"Challenges and Considerations with Code-Mixed NLP for Multilingual Societies","date":"2021-06-15","arxiv_id":"2106.07823","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multilingual-modeling-method-for-span","title":"A Multilingual Modeling Method for Span-Extraction Reading Comprehension","date":"2021-05-31","arxiv_id":"2105.14880","repositories_listed":0,"syntology":null},{"url":"/paper/xlent-mining-a-large-cross-lingual-entity","slug":"xlent-mining-a-large-cross-lingual-entity","title":"XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment","date":"2021-04-17","arxiv_id":"2104.08597","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-and-bias-in-multilingual-nlp","title":"Representation and Bias in Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coreference-strategies-in-english-german","title":"Coreference Strategies in English-German Translation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ive-got-a-construction-looks-funny","title":"I’ve got a construction looks funny – representing and recovering non-standard constructions in UD","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pragmatic-information-in-translation-a-corpus","title":"Pragmatic information in translation: a corpus-based study of tense and mood in English and German","date":"2020-07-10","arxiv_id":"2007.05234","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-parallel-corpus-creation-for-hindi","title":"Automatic Parallel Corpus Creation for Hindi-English News Translation Task","date":"2019-01-24","arxiv_id":"1901.08625","repositories_listed":0,"syntology":null},{"url":null,"slug":"uriel-and-lang2vec-representing-languages-as","title":"URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-multital-nlp-tool-infrastructure","title":"The MultiTal NLP tool infrastructure","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-the-use-of-typological-information","title":"Survey on the Use of Typological Information in Natural Language Processing","date":"2016-10-11","arxiv_id":"1610.03349","repositories_listed":0,"syntology":null},{"url":null,"slug":"dbpedia-abstracts-a-large-scale-open","title":"DBpedia Abstracts: A Large-Scale, Open, Multilingual NLP Training Corpus","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-the-multilingual-semantic","title":"Development of the Multilingual Semantic Annotation System","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ixa-pipeline-efficient-and-ready-to-use","title":"IXA pipeline: Efficient and Ready to Use Multilingual NLP tools","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-clustering-of-pivot-paraphrases","title":"Semantic Clustering of Pivot Paraphrases","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"polyglot-distributed-word-representations-for","title":"Polyglot: Distributed Word Representations for Multilingual NLP","date":"2013-07-05","arxiv_id":"1307.1662","repositories_listed":0,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/multilingual-nlp/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/multilingual-nlp/papers/ran/1","json":"/task/multilingual-nlp/papers/ran/1.json","rows":8}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"0662aa0782f30c5f9a1567f0b62e1b82e37f69a83a309dd6ecf432adfb2e555e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}