{"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/5","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":5,"pages_in_order":8,"rows_per_page":100,"rows":[401,500],"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/papers/4","next":"/task/language-identification/papers/6","papers":[{"url":null,"slug":"lt-helsinki-at-semeval-2020-task-12","title":"LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?","date":"2020-08-03","arxiv_id":"2008.00805","repositories_listed":0,"syntology":null},{"url":null,"slug":"salamnet-at-semeval-2020-task12-deep-learning","title":"SalamNET at SemEval-2020 Task12: Deep Learning Approach for Arabic Offensive Language Detection","date":"2020-07-28","arxiv_id":"2007.13974","repositories_listed":0,"syntology":null},{"url":null,"slug":"duluth-at-semeval-2020-task-12-offensive","title":"Duluth at SemEval-2020 Task 12: Offensive Tweet Identification in English with Logistic Regression","date":"2020-07-25","arxiv_id":"2007.12946","repositories_listed":0,"syntology":null},{"url":null,"slug":"xd-at-semeval-2020-task-12-ensemble-approach","title":"XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders","date":"2020-07-21","arxiv_id":"2007.10945","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-diversity-in-text-summarization-on","title":"Dialect Diversity in Text Summarization on Twitter","date":"2020-07-15","arxiv_id":"2007.07860","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-language-identification-with","title":"Fine-grained Language Identification with Multilingual CapsNet Model","date":"2020-07-12","arxiv_id":"2007.06078","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-asru-2019-mandarin-english-code-switching","title":"The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results","date":"2020-07-12","arxiv_id":"2007.05916","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-selection-on-noisy-twitter-short-text","title":"Feature Selection on Noisy Twitter Short Text Messages for Language Identification","date":"2020-07-11","arxiv_id":"2007.05727","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-end-to-end-bilingual-asr-systems","title":"Streaming End-to-End Bilingual ASR Systems with Joint Language Identification","date":"2020-07-08","arxiv_id":"2007.03900","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-inductive-transfer-to-detect","title":"Cross-lingual Inductive Transfer to Detect Offensive Language","date":"2020-07-07","arxiv_id":"2007.03771","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-report-on-the-2020-vua-and-toefl-metaphor","title":"A Report on the 2020 VUA and TOEFL Metaphor Detection Shared Task","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-assessment-of-language-identification","title":"An Assessment of Language Identification Methods on Tweets and Wikipedia Articles","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gluecos-an-evaluation-benchmark-for-code-1","title":"GLUECoS: An Evaluation Benchmark for Code-Switched NLP","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-effect-of-auxiliary","title":"Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"opusfilter-a-configurable-parallel-corpus","title":"OpusFilter: A Configurable Parallel Corpus Filtering Toolbox","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptation-de-domaine-non-supervis-ee-pour-la","title":"Adaptation de domaine non supervis\\'ee pour la reconnaissance de la langue par r\\'egularisation d'un r\\'eseau de neurones (Unsupervised domain adaptation for language identification by regularization of a neural network)","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lexical-normalization-for-code-switched-data","title":"Lexical Normalization for Code-switched Data and its Effect on POS-tagging","date":"2020-06-01","arxiv_id":"2006.01175","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-language-identification-using","title":"Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses","date":"2020-06-01","arxiv_id":"2006.00703","repositories_listed":0,"syntology":null},{"url":null,"slug":"identification-segmentation-of-indian","title":"Identification/Segmentation of Indian Regional Languages with Singular Value Decomposition based Feature Embedding","date":"2020-05-17","arxiv_id":"2005.08229","repositories_listed":0,"syntology":null},{"url":"/paper/lince-a-centralized-benchmark-for-linguistic","slug":"lince-a-centralized-benchmark-for-linguistic","title":"LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation","date":"2020-05-09","arxiv_id":"2005.04322","repositories_listed":0,"syntology":null},{"url":null,"slug":"liir-at-semeval-2020-task-12-a-cross-lingual","title":"LIIR at SemEval-2020 Task 12: A Cross-Lingual Augmentation Approach for Multilingual Offensive Language Identification","date":"2020-05-07","arxiv_id":"2005.03695","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-web-corpora-for-minority-languages","title":"Building Web Corpora for Minority Languages","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hitachi-at-semeval-2020-task-12-offensive","title":"Hitachi at SemEval-2020 Task 12: Offensive Language Identification with Noisy Labels using Statistical Sampling and Post-Processing","date":"2020-05-01","arxiv_id":"2005.00295","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-performance-of-time-pooling-strategies","title":"On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"opustools-and-parallel-corpus-diagnostics","title":"OpusTools and Parallel Corpus Diagnostics","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"search-query-language-identification-using","title":"Search Query Language Identification Using Weak Labeling","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"two-lrl-distractor-corpora-from-web","title":"Two LRL \\& Distractor Corpora from Web Information Retrieval and a Small Case Study in Language Identification without Training Corpora","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-semi-supervised-dataset-for","title":"SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification","date":"2020-04-29","arxiv_id":"2004.14454","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect-language-of-transliterated-texts","title":"Detect Language of Transliterated Texts","date":"2020-04-26","arxiv_id":"2004.13521","repositories_listed":0,"syntology":null},{"url":null,"slug":"gluecos-an-evaluation-benchmark-for-code","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","date":"2020-04-26","arxiv_id":"2004.12376","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-languages-the-corpus-of-global","title":"Mapping Languages: The Corpus of Global Language Use","date":"2020-04-02","arxiv_id":"2004.00798","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-relevance-and-sequence-modeling-in","title":"Towards Relevance and Sequence Modeling in Language Recognition","date":"2020-04-02","arxiv_id":"2004.01221","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnn-transducer-with-language-bias-for-end-to","title":"Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition","date":"2020-02-19","arxiv_id":"2002.08126","repositories_listed":0,"syntology":null},{"url":null,"slug":"identification-of-indian-languages-using","title":"Identification of Indian Languages using Ghost-VLAD pooling","date":"2020-02-05","arxiv_id":"2002.01664","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-identification-for","title":"Improving Language Identification for Multilingual Speakers","date":"2020-01-29","arxiv_id":"2001.11019","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-and-non-universal-text-statistics","title":"Universal and non-universal text statistics: Clustering coefficient for language identification","date":"2019-11-18","arxiv_id":"1911.08915","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-grammar-induction-with","title":"Multilingual Grammar Induction with Continuous Language Identification","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"normalization-of-indonesian-english-code","title":"Normalization of Indonesian-English Code-Mixed Twitter Data","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"signal-combination-for-language","title":"Signal Combination for Language Identification","date":"2019-10-21","arxiv_id":"1910.09687","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-on-massive-datasets","title":"Language Identification on Massive Datasets of Short Message using an Attention Mechanism CNN","date":"2019-10-15","arxiv_id":"1910.06748","repositories_listed":0,"syntology":null},{"url":"/paper/spoken-language-identification-using-convnets","slug":"spoken-language-identification-using-convnets","title":"Spoken Language Identification using ConvNets","date":"2019-10-09","arxiv_id":"1910.04269","repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-for-the-second-shared-task-on-1","title":"Overview for the Second Shared Task on Language Identification in Code-Switched Data","date":"2019-09-28","arxiv_id":"1909.13016","repositories_listed":0,"syntology":null},{"url":null,"slug":"kashmir-a-computational-analysis-of-the-voice","title":"Hope Speech Detection: A Computational Analysis of the Voice of Peace","date":"2019-09-11","arxiv_id":"1909.12940","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-training-for-chinese-dialect","title":"Two-stage Training for Chinese Dialect Recognition","date":"2019-08-06","arxiv_id":"1908.02284","repositories_listed":0,"syntology":null},{"url":null,"slug":"anglicized-words-and-misspelled-cognates-in","title":"Anglicized Words and Misspelled Cognates in Native Language Identification","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multilingual-meta-embeddings-for","title":"Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regression-or-classification-automated-essay","title":"Regression or classification? Automated Essay Scoring for Norwegian","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-language-identification-of-code","title":"Joint Language Identification of Code-Switching Speech using Attention based E2E Network","date":"2019-07-15","arxiv_id":"1907.06342","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-for-multilingual","title":"Adversarial Training for Multilingual Acoustic Modeling","date":"2019-06-17","arxiv_id":"1906.07093","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-report-on-the-third-vardial-evaluation","title":"A Report on the Third VarDial Evaluation Campaign","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bnu-hkbu-uic-nlp-team-2-at-semeval-2019-task","title":"BNU-HKBU UIC NLP Team 2 at SemEval-2019 Task 6: Detecting Offensive Language Using BERT model","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"camsterdam-at-semeval-2019-task-6-neural-and","title":"CAMsterdam at SemEval-2019 Task 6: Neural and graph-based feature extraction for the identification of offensive tweets","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cn-hit-mit-at-semeval-2019-task-6-offensive","title":"CN-HIT-MI.T at SemEval-2019 Task 6: Offensive Language Identification Based on BiLSTM with Double Attention","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"convai-at-semeval-2019-task-6-offensive","title":"ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deepanalyzer-at-semeval-2019-task-6-a-deep","title":"DeepAnalyzer at SemEval-2019 Task 6: A deep learning-based ensemble method for identifying offensive tweets","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminating-between-mandarin-chinese-and","title":"Discriminating between Mandarin Chinese and Swiss-German varieties using adaptive language models","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emad-at-semeval-2019-task-6-offensive","title":"Emad at SemEval-2019 Task 6: Offensive Language Identification using Traditional Machine Learning and Deep Learning approaches","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"had-tubingen-at-semeval-2019-task-6-deep","title":"HAD-T\\\"ubingen at SemEval-2019 Task 6: Deep Learning Analysis of Offensive Language on Twitter: Identification and Categorization","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hhu-at-semeval-2019-task-6-context-does","title":"HHU at SemEval-2019 Task 6: Context Does Matter - Tackling Offensive Language Identification and Categorization with ELMo","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cuneiform-language-identification","title":"Improving Cuneiform Language Identification with BERT","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-approach-to-deromanization-of-code","title":"Joint Approach to Deromanization of Code-mixed Texts","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-discrimination-and-transfer-learning","title":"Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"naive-bayes-and-bilstm-ensemble-for","title":"Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nuli-at-semeval-2019-task-6-transfer-learning","title":"NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ssn_nlp-at-semeval-2019-task-6-offensive","title":"SSN\\_NLP at SemEval-2019 Task 6: Offensive Language Identification in Social Media using Traditional and Deep Machine Learning Approaches","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-titans-at-semeval-2019-task-6-offensive","title":"The Titans at SemEval-2019 Task 6: Offensive Language Identification, Categorization and Target Identification","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"twistbytes-identification-of-cuneiform","title":"TwistBytes - Identification of Cuneiform Languages and German Dialects at VarDial 2019","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"typological-features-for-multilingual","title":"Typological Features for Multilingual Delexicalised Dependency Parsing","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiclass-language-identification-using-deep","title":"Multiclass Language Identification using Deep Learning on Spectral Images of Audio Signals","date":"2019-05-10","arxiv_id":"1905.04348","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributional-interaction-of-concreteness","title":"Distributional Interaction of Concreteness and Abstractness in Verb--Noun Subcategorisation","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experiments-in-cuneiform-language","title":"Experiments in Cuneiform Language Identification","date":"2019-04-27","arxiv_id":"1904.12087","repositories_listed":0,"syntology":null},{"url":null,"slug":"subword-level-language-identification-for","title":"Subword-Level Language Identification for Intra-Word Code-Switching","date":"2019-04-03","arxiv_id":"1904.01989","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-adaptation-for-language-and","title":"Language Model Adaptation for Language and Dialect Identification of Text","date":"2019-03-26","arxiv_id":"1903.10915","repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2019-task-6-an-exploration-of-state","title":"An Exploration of State-of-the-art Methods for Offensive Language Detection","date":"2019-03-15","arxiv_id":"1903.07445","repositories_listed":0,"syntology":null},{"url":null,"slug":"offenseval-at-semeval-2018-task-6-identifying","title":"Absit invidia verbo: Comparing Deep Learning methods for offensive language","date":"2019-03-14","arxiv_id":"1903.05929","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-and-dialect-identification-of","title":"Language and Dialect Identification of Cuneiform Texts","date":"2019-03-05","arxiv_id":"1903.01891","repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2019-task-6-identifying-and","title":"Towards NLP with Deep Learning: Convolutional Neural Networks and Recurrent Neural Networks for Offensive Language Identification in Social Media","date":"2019-03-02","arxiv_id":"1903.00665","repositories_listed":0,"syntology":null},{"url":null,"slug":"utterance-level-end-to-end-language","title":"Utterance-level end-to-end language identification using attention-based CNN-BLSTM","date":"2019-02-20","arxiv_id":"1902.07374","repositories_listed":0,"syntology":null},{"url":null,"slug":"albanian-language-identification-in-text","title":"Albanian Language Identification in Text Documents","date":"2019-01-14","arxiv_id":"1901.04216","repositories_listed":0,"syntology":null},{"url":null,"slug":"corpora-of-social-media-in-minority-uralic","title":"Corpora of social media in minority Uralic languages","date":"2019-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-attentive-fusion-for-end-to-end","title":"Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain","date":"2018-12-04","arxiv_id":"1812.01501","repositories_listed":0,"syntology":null},{"url":null,"slug":"transductive-learning-with-string-kernels-for","title":"Transductive Learning with String Kernels for Cross-Domain Text Classification","date":"2018-11-02","arxiv_id":"1811.01734","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-to-end-code-switching-speech","title":"Towards End-to-End Code-Switching Speech Recognition","date":"2018-10-31","arxiv_id":"1810.13091","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategies-for-language-identification-in","title":"Strategies for Language Identification in Code-Mixed Low Resource Languages","date":"2018-10-16","arxiv_id":"1810.07156","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-compact-accurate-model-for-language","title":"A Fast, Compact, Accurate Model for Language Identification of Codemixed Text","date":"2018-10-09","arxiv_id":"1810.04142","repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-with-user","title":"Native Language Identification with User Generated Content","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"part-of-speech-tagging-for-code-switched-1","title":"Part-of-Speech Tagging for Code-Switched, Transliterated Texts without Explicit Language Identification","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"similarity-dependent-chinese-restaurant","title":"Similarity Dependent Chinese Restaurant Process for Cognate Identification in Multilingual Wordlists","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-emotions-in-native-language","title":"The Role of Emotions in Native Language Identification","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hindi-english-code-switching-speech-corpus","title":"Hindi-English Code-Switching Speech Corpus","date":"2018-09-24","arxiv_id":"1810.00662","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-with-deep-bottleneck","title":"Language Identification with Deep Bottleneck Features","date":"2018-09-18","arxiv_id":"1809.08909","repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-with","title":"Native Language Identification With Classifier Stacking and Ensembles","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-results-of-string-kernels-in","title":"Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set","date":"2018-08-25","arxiv_id":"1808.08409","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-in-code-mixed-data","title":"Language Identification in Code-Mixed Data using Multichannel Neural Networks and Context Capture","date":"2018-08-21","arxiv_id":"1808.07118","repositories_listed":0,"syntology":null},{"url":null,"slug":"character-level-convolutional-neural-network","title":"Character Level Convolutional Neural Network for Indo-Aryan Language Identification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"computationally-efficient-discrimination","title":"Computationally efficient discrimination between language varieties with large feature vectors and regularized classifiers","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-models-for-arabic-dialect-identification","title":"Deep Models for Arabic Dialect Identification on Benchmarked Data","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-classifier-combinations-for","title":"Exploring Classifier Combinations for Language Variety Identification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-connected-neural-network-with-advance","title":"Fully Connected Neural Network with Advance Preprocessor to Identify Aggression over Facebook and Twitter","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"heli-based-experiments-in-discriminating","title":"HeLI-based Experiments in Discriminating Between Dutch and Flemish Subtitles","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"759fc16a9ae9b82d48a9c2914cd2a6acd4c6732886eb526de2a92d16ca2ad473","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}