{"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/language-identification","name":"Language Identification","slug":"language-identification","description_markdown":"Language identification is the task of determining the language of a text.","categories":[{"name":"Audio","url":"/area/audio"},{"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":794,"papers_with_code":143,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":20,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/language-identification-on-voxlingua107-1","slug":"language-identification-on-voxlingua107-1","dataset":"VOXLINGUA107","dataset_url":"/dataset/voxlingua107","rows_in_archive":2,"metrics":["Error rate"],"first_row_in_archive_order":{"model":"XLS-R","paper_title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","paper_url":"/paper/xls-r-self-supervised-cross-lingual-speech","paper_date":"2021-11-17","arxiv_id":"2111.09296","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"},{"title":"gatech-eic/s3-router","url":"https://github.com/gatech-eic/s3-router"}],"syntology":null}},{"leaderboard":"/sota/language-identification-on-glotlid-c","slug":"language-identification-on-glotlid-c","dataset":"GlotLID-C","dataset_url":null,"rows_in_archive":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"GlotLID","paper_title":"GlotLID: Language Identification for Low-Resource Languages","paper_url":"/paper/glotlid-language-identification-for-low","paper_date":"2023-10-24","arxiv_id":"2310.16248","code_links":[{"title":"cisnlp/glotlid","url":"https://github.com/cisnlp/glotlid"},{"title":"cisnlp/glotstorybook","url":"https://github.com/cisnlp/glotstorybook"},{"title":"cisnlp/glotsparse","url":"https://github.com/cisnlp/glotsparse"}],"syntology":null}},{"leaderboard":"/sota/language-identification-on-nordic-langid","slug":"language-identification-on-nordic-langid","dataset":"Nordic Language Identification","dataset_url":"/dataset/nordic-langid","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FastText","paper_title":"Discriminating Between Similar Nordic Languages","paper_url":"/paper/discriminating-between-similar-nordic","paper_date":"2020-12-11","arxiv_id":"2012.06431","code_links":[{"title":"renhaa/NordicDSL","url":"https://github.com/renhaa/NordicDSL"},{"title":"StrombergNLP/NordicDSL","url":"https://github.com/StrombergNLP/NordicDSL"}],"syntology":null}},{"leaderboard":"/sota/language-identification-on-opensubtitles","slug":"language-identification-on-opensubtitles","dataset":"OpenSubtitles","dataset_url":"/dataset/opensubtitles","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Apple bi-LSTM","paper_title":"A reproduction of Apple's bi-directional LSTM models for language identification in short strings","paper_url":"/paper/a-reproduction-of-apple-s-bi-directional-lstm","paper_date":"2021-02-11","arxiv_id":"2102.06282","code_links":[{"title":"AU-DIS/LSTM_langid","url":"https://github.com/AU-DIS/LSTM_langid"}],"syntology":null}},{"leaderboard":"/sota/language-identification-on-universal","slug":"language-identification-on-universal","dataset":"Universal Dependencies","dataset_url":"/dataset/universal-dependencies","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Apple bi-LSTM","paper_title":"A reproduction of Apple's bi-directional LSTM models for language identification in short strings","paper_url":"/paper/a-reproduction-of-apple-s-bi-directional-lstm","paper_date":"2021-02-11","arxiv_id":"2102.06282","code_links":[{"title":"AU-DIS/LSTM_langid","url":"https://github.com/AU-DIS/LSTM_langid"}],"syntology":null}},{"leaderboard":"/sota/language-identification-on-voxforge","slug":"language-identification-on-voxforge","dataset":"VoxForge","dataset_url":"/dataset/voxforge","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ConformerG-P","paper_title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","paper_url":"/paper/bigssl-exploring-the-frontier-of-large-scale","paper_date":"2021-09-27","arxiv_id":"2109.13226","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/universal-dependencies","name":"Universal Dependencies","full_name":"","num_papers_in_archive":520},{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","num_papers_in_archive":449},{"url":"/dataset/opensubtitles","name":"OpenSubtitles","full_name":"","num_papers_in_archive":214},{"url":"/dataset/olid","name":"OLID","full_name":"Offensive Language Identification Dataset","num_papers_in_archive":152},{"url":"/dataset/conan","name":"CONAN","full_name":"COunter NArratives through Nichesourcing","num_papers_in_archive":27},{"url":"/dataset/moroco","name":"MOROCO","full_name":"MOldavian and ROmanian Dialectal COrpus","num_papers_in_archive":22},{"url":"/dataset/dakshina","name":"Dakshina","full_name":"Dakshina","num_papers_in_archive":14},{"url":"/dataset/voxforge","name":"VoxForge","full_name":"VoxForge","num_papers_in_archive":11},{"url":"/dataset/hindencorp","name":"HindEnCorp","full_name":"","num_papers_in_archive":5},{"url":"/dataset/ogtd","name":"OGTD","full_name":"Offensive Greek Tweet Dataset","num_papers_in_archive":3},{"url":"/dataset/wili-2018","name":"WiLI-2018","full_name":"","num_papers_in_archive":3},{"url":"/dataset/udhr-lid","name":"udhr-lid","full_name":"","num_papers_in_archive":2},{"url":"/dataset/voxlingua107","name":"VOXLINGUA107","full_name":"","num_papers_in_archive":2},{"url":"/dataset/glotsparse","name":"GlotSparse","full_name":"","num_papers_in_archive":1},{"url":"/dataset/glotstorybook","name":"GlotStoryBook","full_name":"","num_papers_in_archive":1},{"url":"/dataset/l3cube-mahacorpus","name":"L3Cube-MahaCorpus","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nli-pt","name":"NLI-PT","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nordic-langid","name":"Nordic Language Identification","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tugebic","name":"TuGebic","full_name":"A Turkish-German Bilingual Code-Switching Corpus","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":[{"url":"/task/dialect-identification","name":"Dialect Identification"},{"url":"/task/native-language-identification","name":"Native Language Identification"}],"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":8,"rows_per_page":100,"shown":100,"of":794,"of_with_code":143,"tagged_in_all":794,"counts":{"archive_papers_tagged":794,"with_a_code_link":143,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":794,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/scaling-speech-technology-to-1000-languages-1","slug":"scaling-speech-technology-to-1000-languages-1","title":"Scaling Speech Technology to 1,000+ Languages","date":"2023-05-22","arxiv_id":"2305.13516","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-speech-technology-to-1000-languages-1#ran","syntology_url":"https://syntology.ai/paper/2305.13516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13516"}},"official":{"repos":["facebookresearch/fairseq","pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/speechbrain-a-general-purpose-speech-toolkit","slug":"speechbrain-a-general-purpose-speech-toolkit","title":"SpeechBrain: A General-Purpose Speech Toolkit","date":"2021-06-08","arxiv_id":"2106.04624","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speechbrain-a-general-purpose-speech-toolkit#ran","syntology_url":"https://syntology.ai/paper/2106.04624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04624"}},"official":{"repos":["speechbrain/speechbrain"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-wili-benchmark-dataset-for-written","slug":"the-wili-benchmark-dataset-for-written","title":"The WiLI benchmark dataset for written language identification","date":"2018-01-23","arxiv_id":"1801.07779","repositories_listed":4,"syntology":null},{"url":"/paper/glotlid-language-identification-for-low","slug":"glotlid-language-identification-for-low","title":"GlotLID: Language Identification for Low-Resource Languages","date":"2023-10-24","arxiv_id":"2310.16248","repositories_listed":3,"syntology":null},{"url":"/paper/cosyvoice-3-towards-in-the-wild-speech","slug":"cosyvoice-3-towards-in-the-wild-speech","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","date":"2025-05-23","arxiv_id":"2505.17589","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cosyvoice-3-towards-in-the-wild-speech#ran","syntology_url":"https://syntology.ai/paper/2505.17589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17589"}},"official":{"repos":["funaudiollm/cosyvoice"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/glotcc-an-open-broad-coverage-commoncrawl","slug":"glotcc-an-open-broad-coverage-commoncrawl","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","date":"2024-10-31","arxiv_id":"2410.23825","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/kinit-at-semeval-2024-task-8-fine-tuned-llms","slug":"kinit-at-semeval-2024-task-8-fine-tuned-llms","title":"KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection","date":"2024-02-21","arxiv_id":"2402.13671","repositories_listed":2,"syntology":null},{"url":"/paper/xls-r-self-supervised-cross-lingual-speech","slug":"xls-r-self-supervised-cross-lingual-speech","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","date":"2021-11-17","arxiv_id":"2111.09296","repositories_listed":2,"syntology":null},{"url":"/paper/discriminating-between-similar-nordic","slug":"discriminating-between-similar-nordic","title":"Discriminating Between Similar Nordic Languages","date":"2020-12-11","arxiv_id":"2012.06431","repositories_listed":2,"syntology":null},{"url":"/paper/adelaidecyc-at-semeval-2020-task-12-ensemble","slug":"adelaidecyc-at-semeval-2020-task-12-ensemble","title":"AdelaideCyC at SemEval-2020 Task 12: Ensemble of Classifiers for Offensive Language Detection in Social Media","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/cybertronics-at-semeval-2020-task-12","slug":"cybertronics-at-semeval-2020-task-12","title":"CyberTronics at SemEval-2020 Task 12: Multilingual Offensive Language Identification over Social Media","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language-1","slug":"voxlingua107-a-dataset-for-spoken-language-1","title":"VoxLingua107: a Dataset for Spoken Language Recognition","date":"2020-11-25","arxiv_id":"2011.12998","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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","sample_list":"/paper/voxlingua107-a-dataset-for-spoken-language-1#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":{"repos":["alumae/torch-xvectors-wav"],"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"]}}},{"url":"/paper/common-voice-a-massively-multilingual-speech","slug":"common-voice-a-massively-multilingual-speech","title":"Common Voice: A Massively-Multilingual Speech Corpus","date":"2019-12-13","arxiv_id":"1912.06670","repositories_listed":2,"syntology":null},{"url":"/paper/speech-vgg-a-deep-feature-extractor-for","slug":"speech-vgg-a-deep-feature-extractor-for","title":"Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing","date":"2019-10-22","arxiv_id":"1910.09909","repositories_listed":2,"syntology":null},{"url":"/paper/semeval-2019-task-6-identifying-and-1","slug":"semeval-2019-task-6-identifying-and-1","title":"SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)","date":"2019-03-19","arxiv_id":"1903.08983","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semeval-2019-task-6-identifying-and-1#ran","syntology_url":"https://syntology.ai/paper/1903.08983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.08983"}},"official":null}},{"url":"/paper/universal-dependency-parsing-for-hindi","slug":"universal-dependency-parsing-for-hindi","title":"Universal Dependency Parsing for Hindi-English Code-switching","date":"2018-04-16","arxiv_id":"1804.05868","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-uto-aztecan-language-technologies-a","slug":"advancing-uto-aztecan-language-technologies-a","title":"Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language","date":"2025-05-10","arxiv_id":"2505.18159","repositories_listed":1,"syntology":null},{"url":"/paper/kreyolid-from-language-identification-towards","slug":"kreyolid-from-language-identification-towards","title":"KréyoLID From Language Identification Towards Language Mining","date":"2025-03-09","arxiv_id":"2503.06547","repositories_listed":1,"syntology":null},{"url":"/paper/english-please-evaluating-machine-translation","slug":"english-please-evaluating-machine-translation","title":"English Please: Evaluating Machine Translation with Large Language Models for Multilingual Bug Reports","date":"2025-02-20","arxiv_id":"2502.14338","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-scandinavian-language","slug":"multi-label-scandinavian-language","title":"Multi-label Scandinavian Language Identification (SLIDE)","date":"2025-02-10","arxiv_id":"2502.06692","repositories_listed":1,"syntology":null},{"url":"/paper/is-it-navajo-accurate-language-detection-in","slug":"is-it-navajo-accurate-language-detection-in","title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages","date":"2025-01-27","arxiv_id":"2501.15773","repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-slu-a-massively-multilingual-benchmark","slug":"fleurs-slu-a-massively-multilingual-benchmark","title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","date":"2025-01-10","arxiv_id":"2501.06117","repositories_listed":1,"syntology":null},{"url":"/paper/afrihubert-a-self-supervised-speech","slug":"afrihubert-a-self-supervised-speech","title":"AfriHuBERT: A self-supervised speech representation model for African languages","date":"2024-09-30","arxiv_id":"2409.20201","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multilingual-asr-in-the-wild-using","slug":"improving-multilingual-asr-in-the-wild-using","title":"Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking","date":"2024-09-27","arxiv_id":"2409.18428","repositories_listed":1,"syntology":null},{"url":"/paper/language-informed-beam-search-decoding-for","slug":"language-informed-beam-search-decoding-for","title":"Language-Informed Beam Search Decoding for Multilingual Machine Translation","date":"2024-08-11","arxiv_id":"2408.05738","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-informed-beam-search-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2408.05738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05738"}},"official":{"repos":["yilinyang7/fairseq_multi_fix"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/speech-massive-a-multilingual-speech-dataset","slug":"speech-massive-a-multilingual-speech-dataset","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","date":"2024-08-07","arxiv_id":"2408.03900","repositories_listed":1,"syntology":null},{"url":"/paper/script-agnostic-language-identification","slug":"script-agnostic-language-identification","title":"Script-Agnostic Language Identification","date":"2024-06-25","arxiv_id":"2406.17901","repositories_listed":1,"syntology":null},{"url":"/paper/an-initial-investigation-of-language","slug":"an-initial-investigation-of-language","title":"An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios","date":"2024-06-13","arxiv_id":"2406.08911","repositories_listed":1,"syntology":null},{"url":"/paper/masklid-code-switching-language","slug":"masklid-code-switching-language","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","date":"2024-06-10","arxiv_id":"2406.06263","repositories_listed":1,"syntology":null},{"url":"/paper/fastspell-the-langid-magic-spell","slug":"fastspell-the-langid-magic-spell","title":"FastSpell: the LangId Magic Spell","date":"2024-04-12","arxiv_id":"2404.08345","repositories_listed":1,"syntology":null},{"url":"/paper/what-is-learnt-by-the-learnable-front-end","slug":"what-is-learnt-by-the-learnable-front-end","title":"What is Learnt by the LEArnable Front-end (LEAF)? Adapting Per-Channel Energy Normalisation (PCEN) to Noisy Conditions","date":"2024-04-10","arxiv_id":"2404.06702","repositories_listed":1,"syntology":null},{"url":"/paper/geographically-informed-language","slug":"geographically-informed-language","title":"Geographically-Informed Language Identification","date":"2024-03-14","arxiv_id":"2403.09892","repositories_listed":1,"syntology":null},{"url":"/paper/language-and-speech-technology-for-central","slug":"language-and-speech-technology-for-central","title":"Language and Speech Technology for Central Kurdish Varieties","date":"2024-03-04","arxiv_id":"2403.01983","repositories_listed":1,"syntology":null},{"url":"/paper/owsm-ctc-an-open-encoder-only-speech","slug":"owsm-ctc-an-open-encoder-only-speech","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","date":"2024-02-20","arxiv_id":"2402.12654","repositories_listed":1,"syntology":null},{"url":"/paper/code-switched-language-identification-is","slug":"code-switched-language-identification-is","title":"Code-Switched Language Identification is Harder Than You Think","date":"2024-02-02","arxiv_id":"2402.01505","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/code-switched-language-identification-is#ran","syntology_url":"https://syntology.ai/paper/2402.01505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01505"}},"official":{"repos":["laurieburchell/cs-lid-harder-than-you-think"],"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"]}}},{"url":"/paper/aboutme-using-self-descriptions-in-webpages","slug":"aboutme-using-self-descriptions-in-webpages","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","date":"2024-01-12","arxiv_id":"2401.06408","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/aboutme-using-self-descriptions-in-webpages#ran","syntology_url":"https://syntology.ai/paper/2401.06408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06408"}},"official":{"repos":["lucy3/whos_filtered"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-ai-for-math-part-i-mathpile-a","slug":"generative-ai-for-math-part-i-mathpile-a","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","date":"2023-12-28","arxiv_id":"2312.17120","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generative-ai-for-math-part-i-mathpile-a#ran","syntology_url":"https://syntology.ai/paper/2312.17120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17120"}},"official":{"repos":["gair-nlp/mathpile"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/offmix-3l-a-novel-code-mixed-dataset-in","slug":"offmix-3l-a-novel-code-mixed-dataset-in","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","date":"2023-10-27","arxiv_id":"2310.18387","repositories_listed":1,"syntology":null},{"url":"/paper/visual-speech-recognition-for-low-resource","slug":"visual-speech-recognition-for-low-resource","title":"Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper","date":"2023-09-15","arxiv_id":"2309.08535","repositories_listed":1,"syntology":null},{"url":"/paper/native-language-identification-with-big-bird","slug":"native-language-identification-with-big-bird","title":"Native Language Identification with Big Bird Embeddings","date":"2023-09-13","arxiv_id":"2309.06923","repositories_listed":1,"syntology":null},{"url":"/paper/my-boli-code-mixed-marathi-english-corpora","slug":"my-boli-code-mixed-marathi-english-corpora","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","date":"2023-06-24","arxiv_id":"2306.14030","repositories_listed":1,"syntology":null},{"url":"/paper/towards-training-bilingual-and-code-switched","slug":"towards-training-bilingual-and-code-switched","title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer","date":"2023-06-14","arxiv_id":"2306.08753","repositories_listed":1,"syntology":null},{"url":"/paper/spoken-language-identification-system-for","slug":"spoken-language-identification-system-for","title":"Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech","date":"2023-06-01","arxiv_id":"2306.00736","repositories_listed":1,"syntology":null},{"url":"/paper/merlion-ccs-challenge-evaluation-plan","slug":"merlion-ccs-challenge-evaluation-plan","title":"MERLIon CCS Challenge Evaluation Plan","date":"2023-05-31","arxiv_id":"2305.19493","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-model-performance-in-language","slug":"investigating-model-performance-in-language","title":"Investigating model performance in language identification: beyond simple error statistics","date":"2023-05-30","arxiv_id":"2305.18925","repositories_listed":1,"syntology":null},{"url":"/paper/merlion-ccs-challenge-a-english-mandarin-code","slug":"merlion-ccs-challenge-a-english-mandarin-code","title":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization","date":"2023-05-30","arxiv_id":"2305.18881","repositories_listed":1,"syntology":null},{"url":"/paper/bhasha-abhijnaanam-native-script-and","slug":"bhasha-abhijnaanam-native-script-and","title":"Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages","date":"2023-05-25","arxiv_id":"2305.15814","repositories_listed":1,"syntology":null},{"url":"/paper/script-normalization-for-unconventional","slug":"script-normalization-for-unconventional","title":"Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities","date":"2023-05-25","arxiv_id":"2305.16407","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-dataset-and-model-for-language","slug":"an-open-dataset-and-model-for-language","title":"An Open Dataset and Model for Language Identification","date":"2023-05-23","arxiv_id":"2305.13820","repositories_listed":1,"syntology":null},{"url":"/paper/limit-language-identification","slug":"limit-language-identification","title":"LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages","date":"2023-05-23","arxiv_id":"2305.14263","repositories_listed":1,"syntology":null},{"url":"/paper/doclangid-improving-few-shot-training-to","slug":"doclangid-improving-few-shot-training-to","title":"DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents","date":"2023-05-03","arxiv_id":"2305.02208","repositories_listed":1,"syntology":null},{"url":"/paper/approaches-to-corpus-creation-for-low","slug":"approaches-to-corpus-creation-for-low","title":"Approaches to Corpus Creation for Low-Resource Language Technology: the Case of Southern Kurdish and Laki","date":"2023-04-03","arxiv_id":"2304.01319","repositories_listed":1,"syntology":null},{"url":"/paper/pali-a-language-identification-benchmark-for","slug":"pali-a-language-identification-benchmark-for","title":"PALI: A Language Identification Benchmark for Perso-Arabic Scripts","date":"2023-04-03","arxiv_id":"2304.01322","repositories_listed":1,"syntology":null},{"url":"/paper/language-variety-identification-with-true","slug":"language-variety-identification-with-true","title":"Language Variety Identification with True Labels","date":"2023-03-02","arxiv_id":"2303.01490","repositories_listed":1,"syntology":null},{"url":"/paper/improving-spoken-language-identification-with","slug":"improving-spoken-language-identification-with","title":"Improving Spoken Language Identification with Map-Mix","date":"2023-02-16","arxiv_id":"2302.08229","repositories_listed":1,"syntology":null},{"url":"/paper/sold-sinhala-offensive-language-dataset","slug":"sold-sinhala-offensive-language-dataset","title":"SOLD: Sinhala Offensive Language Dataset","date":"2022-12-01","arxiv_id":"2212.00851","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-the-type-and-target-of-offensive-1","slug":"predicting-the-type-and-target-of-offensive-1","title":"Predicting the Type and Target of Offensive Social Media Posts in Marathi","date":"2022-11-22","arxiv_id":"2211.12570","repositories_listed":1,"syntology":null},{"url":"/paper/afrolid-a-neural-language-identification-tool","slug":"afrolid-a-neural-language-identification-tool","title":"AfroLID: A Neural Language Identification Tool for African Languages","date":"2022-10-21","arxiv_id":"2210.11744","repositories_listed":1,"syntology":null},{"url":"/paper/italian-language-and-dialect-identification","slug":"italian-language-and-dialect-identification","title":"Italian Language and Dialect Identification and Regional French Variety Detection using Adaptive Naive Bayes","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-curious-case-of-logistic-regression-for","slug":"the-curious-case-of-logistic-regression-for","title":"The Curious Case of Logistic Regression for Italian Languages and Dialects Identification","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-first-neural-machine-translation-system","slug":"the-first-neural-machine-translation-system","title":"The first neural machine translation system for the Erzya language","date":"2022-09-19","arxiv_id":"2209.09368","repositories_listed":1,"syntology":null},{"url":"/paper/indicsuperb-a-speech-processing-universal","slug":"indicsuperb-a-speech-processing-universal","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","date":"2022-08-24","arxiv_id":"2208.11761","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/indicsuperb-a-speech-processing-universal#ran","syntology_url":"https://syntology.ai/paper/2208.11761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11761"}},"official":{"repos":["AI4Bharat/indicSUPERB"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/distilled-non-semantic-speech-embeddings-with","slug":"distilled-non-semantic-speech-embeddings-with","title":"Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices","date":"2022-07-12","arxiv_id":"2207.05784","repositories_listed":1,"syntology":null},{"url":"/paper/tweetnlp-cutting-edge-natural-language","slug":"tweetnlp-cutting-edge-natural-language","title":"TweetNLP: Cutting-Edge Natural Language Processing for Social Media","date":"2022-06-29","arxiv_id":"2206.14774","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/tweetnlp-cutting-edge-natural-language#ran","syntology_url":"https://syntology.ai/paper/2206.14774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.14774"}},"official":{"repos":["cardiffnlp/tweetnlp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/language-identification-for-austronesian","slug":"language-identification-for-austronesian","title":"Language Identification for Austronesian Languages","date":"2022-06-09","arxiv_id":"2206.04327","repositories_listed":1,"syntology":null},{"url":"/paper/geezswitch-language-identification-in","slug":"geezswitch-language-identification-in","title":"GeezSwitch: Language Identification in Typologically Related Low-resourced East African Languages","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/word-level-language-identification-using","slug":"word-level-language-identification-using","title":"Word-level Language Identification Using Subword Embeddings for Code-mixed Bangla-English Social Media Data","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-few-shot-learning-evaluation-of","slug":"fleurs-few-shot-learning-evaluation-of","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","date":"2022-05-25","arxiv_id":"2205.12446","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-preference-aware-language-1","slug":"unsupervised-preference-aware-language-1","title":"Unsupervised Preference-Aware Language Identification","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/l3cube-hingcorpus-and-hingbert-a-code-mixed","slug":"l3cube-hingcorpus-and-hingbert-a-code-mixed","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","date":"2022-04-18","arxiv_id":"2204.08398","repositories_listed":1,"syntology":null},{"url":"/paper/pho-lid-a-unified-model-incorporating","slug":"pho-lid-a-unified-model-incorporating","title":"PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification","date":"2022-03-23","arxiv_id":"2203.12366","repositories_listed":1,"syntology":null},{"url":"/paper/geographic-adaptation-of-pretrained-language","slug":"geographic-adaptation-of-pretrained-language","title":"Geographic Adaptation of Pretrained Language Models","date":"2022-03-16","arxiv_id":"2203.08565","repositories_listed":1,"syntology":null},{"url":"/paper/enhance-language-identification-using-dual","slug":"enhance-language-identification-using-dual","title":"Enhance Language Identification using Dual-mode Model with Knowledge Distillation","date":"2022-03-07","arxiv_id":"2203.03218","repositories_listed":1,"syntology":null},{"url":"/paper/bert-lid-leveraging-bert-to-improve-spoken","slug":"bert-lid-leveraging-bert-to-improve-spoken","title":"BERT-LID: Leveraging BERT to Improve Spoken Language Identification","date":"2022-03-01","arxiv_id":"2203.00328","repositories_listed":1,"syntology":null},{"url":"/paper/attentive-temporal-pooling-for-conformer","slug":"attentive-temporal-pooling-for-conformer","title":"Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech","date":"2022-02-24","arxiv_id":"2202.12163","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-into-the-contribution-of","slug":"an-investigation-into-the-contribution-of","title":"An Investigation into the Contribution of Locally Aggregated Descriptors to Figurative Language Identification","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hyperseed-unsupervised-learning-with-vector","slug":"hyperseed-unsupervised-learning-with-vector","title":"Hyperseed: Unsupervised Learning with Vector Symbolic Architectures","date":"2021-10-15","arxiv_id":"2110.08343","repositories_listed":1,"syntology":null},{"url":"/paper/psg-hasoc-dravidian-codemixfire2021","slug":"psg-hasoc-dravidian-codemixfire2021","title":"Pretrained Transformers for Offensive Language Identification in Tanglish","date":"2021-10-06","arxiv_id":"2110.02852","repositories_listed":1,"syntology":null},{"url":"/paper/upv-at-checkthat-2021-mitigating-cultural","slug":"upv-at-checkthat-2021-mitigating-cultural","title":"UPV at CheckThat! 2021: Mitigating Cultural Differences for Identifying Multilingual Check-worthy Claims","date":"2021-09-19","arxiv_id":"2109.09232","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-language-specificity-of-multilingual","slug":"on-the-language-specificity-of-multilingual","title":"On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning","date":"2021-09-14","arxiv_id":"2109.06935","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-offensive-language","slug":"cross-lingual-offensive-language","title":"Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi","date":"2021-09-08","arxiv_id":"2109.03552","repositories_listed":1,"syntology":null},{"url":"/paper/offensive-language-identification-in-low","slug":"offensive-language-identification-in-low","title":"Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling","date":"2021-08-27","arxiv_id":"2108.12177","repositories_listed":1,"syntology":null},{"url":"/paper/sn-computer-science-towards-offensive","slug":"sn-computer-science-towards-offensive","title":"Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts","date":"2021-08-24","arxiv_id":"2108.10939","repositories_listed":1,"syntology":null},{"url":"/paper/dravidiancodemix-sentiment-analysis-and","slug":"dravidiancodemix-sentiment-analysis-and","title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text","date":"2021-06-17","arxiv_id":"2106.09460","repositories_listed":1,"syntology":null},{"url":"/paper/singing-language-identification-using-a-deep","slug":"singing-language-identification-using-a-deep","title":"Singing Language Identification using a Deep Phonotactic Approach","date":"2021-05-31","arxiv_id":"2105.15014","repositories_listed":1,"syntology":null},{"url":"/paper/using-radio-archives-for-low-resource-speech","slug":"using-radio-archives-for-low-resource-speech","title":"Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users","date":"2021-04-27","arxiv_id":"2104.13083","repositories_listed":1,"syntology":null},{"url":"/paper/iiitk-dravidianlangtech-eacl2021-offensive","slug":"iiitk-dravidianlangtech-eacl2021-offensive","title":"IIITK@DravidianLangTech-EACL2021: Offensive Language Identification and Meme Classification in Tamil, Malayalam and Kannada","date":"2021-04-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comparing-the-performance-of-cnns-and-shallow","slug":"comparing-the-performance-of-cnns-and-shallow","title":"Comparing the Performance of CNNs and Shallow Models for Language Identification","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dosa-dravidian-code-mixed-offensive-span","slug":"dosa-dravidian-code-mixed-offensive-span","title":"DOSA: Dravidian Code-Mixed Offensive Span Identification Dataset","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/iiitt-dravidianlangtech-eacl2021-transfer","slug":"iiitt-dravidianlangtech-eacl2021-transfer","title":"IIITT@DravidianLangTech-EACL2021: Transfer Learning for Offensive Language Detection in Dravidian Languages","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-offensive-language-identification-for","slug":"towards-offensive-language-identification-for","title":"Towards Offensive Language Identification for Dravidian Languages","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hate-alert-dravidianlangtech-eacl2021","slug":"hate-alert-dravidianlangtech-eacl2021","title":"Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detection","date":"2021-02-19","arxiv_id":"2102.10084","repositories_listed":1,"syntology":null},{"url":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021","title":"indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":"2102.07150","repositories_listed":1,"syntology":null},{"url":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021-1","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021-1","title":"indicnlp@ kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-reproduction-of-apple-s-bi-directional-lstm","slug":"a-reproduction-of-apple-s-bi-directional-lstm","title":"A reproduction of Apple's bi-directional LSTM models for language identification in short strings","date":"2021-02-11","arxiv_id":"2102.06282","repositories_listed":1,"syntology":null},{"url":"/paper/sj-aj-dravidianlangtech-eacl2021-task","slug":"sj-aj-dravidianlangtech-eacl2021-task","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","date":"2021-02-01","arxiv_id":"2102.01051","repositories_listed":1,"syntology":null},{"url":"/paper/triplet-entropy-loss-improving-the","slug":"triplet-entropy-loss-improving-the","title":"Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems","date":"2020-12-03","arxiv_id":"2012.03775","repositories_listed":1,"syntology":null},{"url":"/paper/fbk-dh-at-semeval-2020-task-12-using-multi","slug":"fbk-dh-at-semeval-2020-task-12-using-multi","title":"FBK-DH at SemEval-2020 Task 12: Using Multi-channel BERT for Multilingual Offensive Language Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stil-simultaneous-slot-filling-translation-1","slug":"stil-simultaneous-slot-filling-translation-1","title":"STIL - Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":11,"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":14,"papers_where_code_ran_first_page":"/task/language-identification/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":"archive","page":2,"of":8,"url":"/task/language-identification/papers/2","json":"/task/language-identification/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/language-identification/papers/3","json":"/task/language-identification/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/language-identification/papers/4","json":"/task/language-identification/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/language-identification/papers/5","json":"/task/language-identification/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/language-identification/papers/6","json":"/task/language-identification/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/language-identification/papers/7","json":"/task/language-identification/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/language-identification/papers/8","json":"/task/language-identification/papers/8.json","rows":94},{"order":"ran","page":1,"of":1,"url":"/task/language-identification/papers/ran/1","json":"/task/language-identification/papers/ran/1.json","rows":14}],"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":"6732de3feb574c434b5e2c1fff23ec212c0b2421b7979b1c253ba43cfd683217","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}