{"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/papers/2","list_of":"/task/language-identification","task":"Language Identification","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":8,"rows_per_page":100,"rows":[101,200],"of":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"},"first_page":"/task/language-identification","prev":"/task/language-identification","next":"/task/language-identification/papers/3","papers":[{"url":"/paper/tac-at-semeval-2020-task-12-ensembling","slug":"tac-at-semeval-2020-task-12-ensembling","title":"TAC at SemEval-2020 Task 12: Ensembling Approach for Multilingual Offensive Language Identification in Social Media","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-id-in-the-wild-unexpected-challenges","slug":"language-id-in-the-wild-unexpected-challenges","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus","date":"2020-10-27","arxiv_id":"2010.14571","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-end-to-end-multilingual-speech","slug":"large-scale-end-to-end-multilingual-speech","title":"Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task Learning","date":"2020-10-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-offensive-language","slug":"multilingual-offensive-language","title":"Multilingual Offensive Language Identification with Cross-lingual Embeddings","date":"2020-10-11","arxiv_id":"2010.05324","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/multilingual-offensive-language#ran","syntology_url":"https://syntology.ai/paper/2010.05324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05324"}},"official":{"repos":["tharindudr/DeepOffense"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/stil-simultaneous-slot-filling-translation","slug":"stil-simultaneous-slot-filling-translation","title":"STIL -- Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++","date":"2020-10-02","arxiv_id":"2010.00760","repositories_listed":1,"syntology":null},{"url":"/paper/ghmerti-at-semeval-2019-task-6-a-deep-word-1","slug":"ghmerti-at-semeval-2019-task-6-a-deep-word-1","title":"Ghmerti at SemEval-2019 Task 6: A Deep Word- and Character-based Approach to Offensive Language Identification","date":"2020-09-22","arxiv_id":"2009.10792","repositories_listed":1,"syntology":null},{"url":"/paper/nlpdove-at-semeval-2020-task-12-improving","slug":"nlpdove-at-semeval-2020-task-12-improving","title":"NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer","date":"2020-08-04","arxiv_id":"2008.01354","repositories_listed":1,"syntology":null},{"url":"/paper/cross-domain-adaptation-of-spoken-language","slug":"cross-domain-adaptation-of-spoken-language","title":"Cross-Domain Adaptation of Spoken Language Identification for Related Languages: The Curious Case of Slavic Languages","date":"2020-08-02","arxiv_id":"2008.00545","repositories_listed":1,"syntology":null},{"url":"/paper/kuisail-at-semeval-2020-task-12-bert-cnn-for","slug":"kuisail-at-semeval-2020-task-12-bert-cnn-for","title":"KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media","date":"2020-07-26","arxiv_id":"2007.13184","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/kuisail-at-semeval-2020-task-12-bert-cnn-for#ran","syntology_url":"https://syntology.ai/paper/2007.13184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13184"}},"official":{"repos":["alisafaya/OffensEval2020"],"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"]}}},{"url":"/paper/problemconquero-at-semeval-2020-task-12","slug":"problemconquero-at-semeval-2020-task-12","title":"problemConquero at SemEval-2020 Task 12: Transformer and Soft label-based approaches","date":"2020-07-21","arxiv_id":"2007.10877","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-language-neutrality-of-pre-trained","slug":"on-the-language-neutrality-of-pre-trained","title":"On the Language Neutrality of Pre-trained Multilingual Representations","date":"2020-04-09","arxiv_id":"2004.05160","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-the-language-neutrality-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2004.05160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05160"}},"official":{"repos":["jlibovicky/assess-multilingual-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/offensive-language-identification-in-greek","slug":"offensive-language-identification-in-greek","title":"Offensive Language Identification in Greek","date":"2020-03-16","arxiv_id":"2003.07459","repositories_listed":1,"syntology":null},{"url":"/paper/short-text-language-identification-for-under","slug":"short-text-language-identification-for-under","title":"Short Text Language Identification for Under Resourced Languages","date":"2019-11-18","arxiv_id":"1911.07555","repositories_listed":1,"syntology":null},{"url":"/paper/from-english-to-code-switching-transfer","slug":"from-english-to-code-switching-transfer","title":"From English to Code-Switching: Transfer Learning with Strong Morphological Clues","date":"2019-09-11","arxiv_id":"1909.05158","repositories_listed":1,"syntology":null},{"url":"/paper/topics-to-avoid-demoting-latent-confounds-in","slug":"topics-to-avoid-demoting-latent-confounds-in","title":"Topics to Avoid: Demoting Latent Confounds in Text Classification","date":"2019-09-01","arxiv_id":"1909.00453","repositories_listed":1,"syntology":null},{"url":"/paper/towards-ethical-content-based-detection-of","slug":"towards-ethical-content-based-detection-of","title":"Towards Ethical Content-Based Detection of Online Influence Campaigns","date":"2019-08-29","arxiv_id":"1908.11030","repositories_listed":1,"syntology":null},{"url":"/paper/embeddia-at-semeval-2019-task-6-detecting","slug":"embeddia-at-semeval-2019-task-6-detecting","title":"Embeddia at SemEval-2019 Task 6: Detecting Hate with Neural Network and Transfer Learning Approaches","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ju_etce_17_21-at-semeval-2019-task-6","slug":"ju_etce_17_21-at-semeval-2019-task-6","title":"JU\\_ETCE\\_17\\_21 at SemEval-2019 Task 6: Efficient Machine Learning and Neural Network Approaches for Identifying and Categorizing Offensive Language in Tweets","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/combination-of-multiple-deep-learning","slug":"combination-of-multiple-deep-learning","title":"Combination of multiple Deep Learning architectures for Offensive Language Detection in Tweets","date":"2019-03-16","arxiv_id":"1903.08734","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-the-type-and-target-of-offensive","slug":"predicting-the-type-and-target-of-offensive","title":"Predicting the Type and Target of Offensive Posts in Social Media","date":"2019-02-25","arxiv_id":"1902.09666","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-development-of-a-large-scale-corpus","slug":"on-the-development-of-a-large-scale-corpus","title":"On the Development of a Large Scale Corpus for Native Language Identification","date":"2018-12-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tuplemax-loss-for-language-identification","slug":"tuplemax-loss-for-language-identification","title":"Tuplemax Loss for Language Identification","date":"2018-11-29","arxiv_id":"1811.12290","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-end-to-end-solution-to-mandarin","slug":"on-the-end-to-end-solution-to-mandarin","title":"On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition","date":"2018-11-01","arxiv_id":"1811.00241","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-language-identification-using","slug":"end-to-end-language-identification-using","title":"End-to-end Language Identification using NetFV and NetVLAD","date":"2018-09-09","arxiv_id":"1809.02906","repositories_listed":1,"syntology":null},{"url":"/paper/aggressive-language-identification-using-word","slug":"aggressive-language-identification-using-word","title":"Aggressive Language Identification Using Word Embeddings and Sentiment Features","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/measuring-language-distance-among-historical","slug":"measuring-language-distance-among-historical","title":"Measuring language distance among historical varieties using perplexity. Application to European Portuguese.","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/using-language-learner-data-for-metaphor","slug":"using-language-learner-data-for-metaphor","title":"Using Language Learner Data for Metaphor Detection","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/whats-in-a-domain-learning-domain-robust-text","slug":"whats-in-a-domain-learning-domain-robust-text","title":"What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Training","date":"2018-05-16","arxiv_id":"1805.06088","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-multi-class-sentiment","slug":"multilingual-multi-class-sentiment","title":"Multilingual Multi-class Sentiment Classification Using Convolutional Neural Networks","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automatic-language-identification-in-texts-a","slug":"automatic-language-identification-in-texts-a","title":"Automatic Language Identification in Texts: A Survey","date":"2018-04-22","arxiv_id":"1804.08186","repositories_listed":1,"syntology":null},{"url":"/paper/improved-text-language-identification-for-the","slug":"improved-text-language-identification-for-the","title":"Improved Text Language Identification for the South African Languages","date":"2017-11-01","arxiv_id":"1711.00247","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-n-gram-and-embedding","slug":"a-study-of-n-gram-and-embedding","title":"A study of N-gram and Embedding Representations for Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-identification-using-deep","slug":"language-identification-using-deep","title":"Language Identification Using Deep Convolutional Recurrent Neural Networks","date":"2017-08-16","arxiv_id":"1708.04811","repositories_listed":1,"syntology":null},{"url":"/paper/joint-ud-parsing-of-norwegian-bokmal-and","slug":"joint-ud-parsing-of-norwegian-bokmal-and","title":"Joint UD Parsing of Norwegian Bokm\\aal and Nynorsk","date":"2017-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/discriminating-between-similar-languages-3","slug":"discriminating-between-similar-languages-3","title":"Discriminating between Similar Languages using Weighted Subword Features","date":"2017-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lanidenn-multilingual-language-identification","slug":"lanidenn-multilingual-language-identification","title":"LanideNN: Multilingual Language Identification on Character Window","date":"2017-01-12","arxiv_id":"1701.03338","repositories_listed":1,"syntology":null},{"url":"/paper/heli-a-word-based-backoff-method-for-language","slug":"heli-a-word-based-backoff-method-for-language","title":"HeLI, a Word-Based Backoff Method for Language Identification","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-character-word-models-for","slug":"hierarchical-character-word-models-for","title":"Hierarchical Character-Word Models for Language Identification","date":"2016-08-10","arxiv_id":"1608.03030","repositories_listed":1,"syntology":null},{"url":"/paper/a-semisupervised-approach-for-language","slug":"a-semisupervised-approach-for-language","title":"A Semisupervised Approach for Language Identification based on Ladder Networks","date":"2016-04-01","arxiv_id":"1604.00317","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-dialect-detection-in-arabic","slug":"automatic-dialect-detection-in-arabic","title":"Automatic Dialect Detection in Arabic Broadcast Speech","date":"2015-09-23","arxiv_id":"1509.06928","repositories_listed":1,"syntology":null},{"url":"/paper/tweetcat-a-tool-for-building-twitter-corpora","slug":"tweetcat-a-tool-for-building-twitter-corpora","title":"TweetCaT: a tool for building Twitter corpora of smaller languages","date":"2014-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/crawling-microblogging-services-to-gather","slug":"crawling-microblogging-services-to-gather","title":"Crawling microblogging services to gather language-classified URLs. Workflow and case study","date":"2013-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/finding-structure-in-text-genome-and-other","slug":"finding-structure-in-text-genome-and-other","title":"Finding Structure in Text, Genome and Other Symbolic Sequences","date":"2012-07-08","arxiv_id":"1207.1847","repositories_listed":1,"syntology":null},{"url":null,"slug":"2506-08400","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","date":"2025-06-10","arxiv_id":"2506.08400","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08564","title":"Neighbors and relatives: How do speech embeddings reflect linguistic connections across the world?","date":"2025-06-10","arxiv_id":"2506.08564","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-semantic-anchoring-in-iso-639-2023","title":"Recursive Semantic Anchoring in ISO 639:2023: A Structural Extension to ISO/TC 37 Frameworks","date":"2025-06-07","arxiv_id":"2506.06870","repositories_listed":0,"syntology":null},{"url":null,"slug":"taltech-systems-for-the-interspeech-2025-ml","title":"TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge","date":"2025-06-02","arxiv_id":"2506.01458","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-multilingual-speech-models-on-ml","title":"Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC","date":"2025-05-30","arxiv_id":"2505.24200","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-masking-improves-transformer-based-text","title":"Token Masking Improves Transformer-Based Text Classification","date":"2025-05-16","arxiv_id":"2505.11746","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-informally-romanized-language","title":"Improving Informally Romanized Language Identification","date":"2025-04-30","arxiv_id":"2504.21540","repositories_listed":0,"syntology":null},{"url":null,"slug":"im-possibility-of-automated-hallucination","title":"(Im)possibility of Automated Hallucination Detection in Large Language Models","date":"2025-04-23","arxiv_id":"2504.17004","repositories_listed":0,"syntology":null},{"url":null,"slug":"comi-lingua-expert-annotated-large-scale","title":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","date":"2025-03-27","arxiv_id":"2503.21670","repositories_listed":0,"syntology":null},{"url":null,"slug":"nusaaksara-a-multimodal-and-multilingual","title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","date":"2025-02-25","arxiv_id":"2502.18148","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-use-of-performer-and-agent-attention","title":"On the use of Performer and Agent Attention for Spoken Language Identification","date":"2025-02-09","arxiv_id":"2502.05841","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-standard-and-dialectal-frisian-asr","title":"Evaluating Standard and Dialectal Frisian ASR: Multilingual Fine-tuning and Language Identification for Improved Low-resource Performance","date":"2025-02-07","arxiv_id":"2502.04883","repositories_listed":0,"syntology":null},{"url":null,"slug":"indonesian-english-code-switching-speech","title":"Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID","date":"2024-12-26","arxiv_id":"2412.19043","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-code-switching-asr-leveraging-non","title":"Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection","date":"2024-11-26","arxiv_id":"2412.08651","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-facets-of-language-generation-in","title":"Exploring Facets of Language Generation in the Limit","date":"2024-11-22","arxiv_id":"2411.15364","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-adversarial-attacks-by-large-language","title":"Can adversarial attacks by large language models be attributed?","date":"2024-11-12","arxiv_id":"2411.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-approaches-to-arabic-english","title":"Computational Approaches to Arabic-English Code-Switching","date":"2024-10-17","arxiv_id":"2410.13318","repositories_listed":0,"syntology":null},{"url":null,"slug":"generation-through-the-lens-of-learning","title":"Generation through the lens of learning theory","date":"2024-10-17","arxiv_id":"2410.13714","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-task-text-classification-pipeline","title":"A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets","date":"2024-10-14","arxiv_id":"2410.10290","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-identifying-low-quality-language","title":"Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset","date":"2024-10-05","arxiv_id":"2410.04292","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-open-source-large-language-models-1","title":"Leveraging Open-Source Large Language Models for Native Language Identification","date":"2024-09-15","arxiv_id":"2409.09659","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-code-switching-speech-recognition-1","title":"Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model","date":"2024-09-03","arxiv_id":"2409.02050","repositories_listed":0,"syntology":null},{"url":null,"slug":"literary-and-colloquial-dialect","title":"Literary and Colloquial Dialect Identification for Tamil using Acoustic Features","date":"2024-08-27","arxiv_id":"2408.14887","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generalized-offensive-language","title":"Towards Generalized Offensive Language Identification","date":"2024-07-26","arxiv_id":"2407.18738","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recipe-of-parallel-corpora-exploitation-for","title":"A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models","date":"2024-06-29","arxiv_id":"2407.00436","repositories_listed":0,"syntology":null},{"url":null,"slug":"sc-moe-switch-conformer-mixture-of-experts","title":"SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR","date":"2024-06-26","arxiv_id":"2406.18021","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-language-adaptation-for-multilingual","title":"Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting","date":"2024-06-18","arxiv_id":"2406.12611","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-spoken-language-identification","title":"Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech","date":"2024-06-13","arxiv_id":"2406.09290","repositories_listed":0,"syntology":null},{"url":null,"slug":"ml-superb-2-0-benchmarking-multilingual","title":"ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets","date":"2024-06-12","arxiv_id":"2406.08641","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-language-identification-for-language","title":"Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation","date":"2024-06-12","arxiv_id":"2406.10276","repositories_listed":0,"syntology":null},{"url":null,"slug":"malayalam-sign-language-identification-using","title":"Malayalam Sign Language Identification using Finetuned YOLOv8 and Computer Vision Techniques","date":"2024-05-08","arxiv_id":"2405.06702","repositories_listed":0,"syntology":null},{"url":null,"slug":"whispy-adapting-stt-whisper-models-to-real","title":"Whispy: Adapting STT Whisper Models to Real-Time Environments","date":"2024-05-06","arxiv_id":"2405.03484","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-federated-learning-approach-to-privacy","title":"A Federated Learning Approach to Privacy Preserving Offensive Language Identification","date":"2024-04-17","arxiv_id":"2404.11470","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-than-words-advancements-and-challenges","title":"More than words: Advancements and challenges in speech recognition for singing","date":"2024-03-14","arxiv_id":"2403.09298","repositories_listed":0,"syntology":null},{"url":null,"slug":"validating-and-exploring-large-geographic","title":"Validating and Exploring Large Geographic Corpora","date":"2024-03-13","arxiv_id":"2403.08198","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-speech-to-languages-to-enhance-code","title":"Aligning Speech to Languages to Enhance Code-switching Speech Recognition","date":"2024-03-09","arxiv_id":"2403.05887","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-structured-language-alternations-in","title":"Detecting Structured Language Alternations in Historical Documents by Combining Language Identification with Fourier Analysis","date":"2024-01-25","arxiv_id":"2401.14569","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-characterization-of-speech-rhythm","title":"Acoustic characterization of speech rhythm: going beyond metrics with recurrent neural networks","date":"2024-01-22","arxiv_id":"2401.14416","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-detection-for-transliterated-content","title":"Language Detection for Transliterated Content","date":"2024-01-09","arxiv_id":"2401.04619","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-linguistic-representation-for","title":"Generative linguistic representation for spoken language identification","date":"2023-12-18","arxiv_id":"2312.10964","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-linguistic-offensive-language-detection","title":"Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media","date":"2023-12-16","arxiv_id":"2312.10528","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-language-id-to-calculate","title":"Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition","date":"2023-12-15","arxiv_id":"2312.09583","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-adaptation-for-code","title":"Attention-Guided Adaptation for Code-Switching Speech Recognition","date":"2023-12-14","arxiv_id":"2312.08856","repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-with-large","title":"Native Language Identification with Large Language Models","date":"2023-12-13","arxiv_id":"2312.07819","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-adaptive-pre-training-of","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","date":"2023-12-12","arxiv_id":"2312.07338","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"offensive-language-identification-in-1","title":"Offensive Language Identification in Transliterated and Code-Mixed Bangla","date":"2023-11-25","arxiv_id":"2311.15023","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-obscure-limitation-of-modular","title":"The Obscure Limitation of Modular Multilingual Language Models","date":"2023-11-21","arxiv_id":"2311.12375","repositories_listed":0,"syntology":null},{"url":null,"slug":"fumbling-in-babel-an-investigation-into","title":"Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability","date":"2023-11-16","arxiv_id":"2311.09696","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-accent-dialect-identification-and","title":"Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognition","date":"2023-10-17","arxiv_id":"2310.11004","repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-2023-ml-superb-challenge-pre","title":"Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond","date":"2023-10-09","arxiv_id":"2310.05513","repositories_listed":0,"syntology":null},{"url":null,"slug":"wavelet-scattering-transform-for-improving","title":"Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification","date":"2023-10-01","arxiv_id":"2310.00602","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-modeling-for-spoken-language","title":"Multimodal Modeling For Spoken Language Identification","date":"2023-09-19","arxiv_id":"2309.10567","repositories_listed":0,"syntology":null},{"url":"/paper/culturax-a-cleaned-enormous-and-multilingual","slug":"culturax-a-cleaned-enormous-and-multilingual","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","date":"2023-09-17","arxiv_id":"2309.09400","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-open-set-spoken-language","title":"Robust Open-Set Spoken Language Identification and the CU MultiLang Dataset","date":"2023-08-29","arxiv_id":"2308.14951","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-llama-2-large-language-models-for","title":"Fine-Tuning Llama 2 Large Language Models for Detecting Online Sexual Predatory Chats and Abusive Texts","date":"2023-08-28","arxiv_id":"2308.14683","repositories_listed":0,"syntology":null}],"record_sha256":"6d6a5d50c034ef8cf08f881a2d072716615d539932e504e1408be212c78b1a33","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}