{"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/6","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":6,"pages_in_order":8,"rows_per_page":100,"rows":[501,600],"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/5","next":"/task/language-identification/papers/7","papers":[{"url":null,"slug":"heli-based-experiments-in-swiss-german","title":"HeLI-based Experiments in Swiss German Dialect Identification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iit-bhu-system-for-indo-aryan-language","title":"IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-language-model-adaptation-for-indo","title":"Iterative Language Model Adaptation for Indo-Aryan Language Identification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-and-the-shifting-sands-of-domain","title":"Language and the Shifting Sands of Domain, Space and Time (Invited Talk)","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-and-morphosyntactic","title":"Language Identification and Morphosyntactic Tagging: The Second VarDial Evaluation Campaign","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-architectures-for-arabic","title":"Neural Network Architectures for Arabic Dialect Identification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-as-native-language-interference","title":"Punctuation as Native Language Interference","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ta14bingen-oslo-team-at-the-vardial-2018","title":"T\\\"ubingen-Oslo Team at the VarDial 2018 Evaluation Campaign: An Analysis of N-gram Features in Language Variety Identification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminating-between-indo-aryan-languages","title":"Discriminating between Indo-Aryan Languages Using SVM Ensembles","date":"2018-07-09","arxiv_id":"1807.03108","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-detection-of-code-switching-style","title":"Automatic Detection of Code-switching Style from Acoustics","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-token-and-turn-level-language","title":"Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switched-named-entity-recognition-with","title":"Code-Switched Named Entity Recognition with Embedding Attention","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-and-analysis-of-code","title":"Language Identification and Analysis of Code-Switched Social Media Text","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-and-named-entity","title":"Language Identification and Named Entity Recognition in Hinglish Code Mixed Tweets","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-for-code-mixing-the-role-of","title":"Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"named-entity-recognition-on-code-switched-1","title":"Named Entity Recognition on Code-Switched Data Using Conditional Random Fields","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-features-for-strong-performance-on","title":"Simple Features for Strong Performance on Named Entity Recognition in Code-Switched Twitter Data","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transliteration-better-than-translation","title":"Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"twitter-universal-dependency-parsing-for","title":"Twitter Universal Dependency Parsing for African-American and Mainstream American English","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-language-identification-for-romance","title":"Automatic Language Identification for Romance Languages using Stop Words and Diacritics","date":"2018-06-14","arxiv_id":"1806.05480","repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-prediction-in-english-hindi-code-mixed","title":"Gender Prediction in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System","date":"2018-06-14","arxiv_id":"1806.05600","repositories_listed":0,"syntology":null},{"url":null,"slug":"addition-of-code-mixed-features-to-enhance","title":"Addition of Code Mixed Features to Enhance the Sentiment Prediction of Song Lyrics","date":"2018-06-11","arxiv_id":"1806.03821","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-character-neural-language","title":"A Comparison of Character Neural Language Model and Bootstrapping for Language Identification in Multilingual Noisy Texts","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-corpus-native-language-identification","title":"Cross-corpus Native Language Identification via Statistical Embedding","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-features-of-sarcasm-and-metaphor","title":"Linguistic Features of Sarcasm and Metaphor Production Quality","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-foreign-language-usage-from","title":"Predicting Foreign Language Usage from English-Only Social Media Posts","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ta14bingen-oslo-at-semeval-2018-task-2-svms","title":"T\\\"ubingen-Oslo at SemEval-2018 Task 2: SVMs perform better than RNNs in Emoji Prediction","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-classifier-features-to-determine","title":"Using Classifier Features to Determine Language Transfer on Morphemes","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-regression-model-of-recurrent-deep-neural","title":"A Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech","date":"2018-05-08","arxiv_id":"1805.02958","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-dialect-identification-in-the-context","title":"Arabic Dialect Identification in the Context of Bivalency and Code-Switching","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-identification-of-maghreb-dialects","title":"Automatic Identification of Maghreb Dialects Using a Dictionary-Based Approach","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-a-tocfl-learner-corpus-for-chinese","title":"Building a TOCFL Learner Corpus for Chinese Grammatical Error Diagnosis","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-parallel-monolingual-gan-chinese","title":"Building Parallel Monolingual Gan Chinese Dialects Corpus","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-closely-related-sub","title":"Classification of Closely Related Sub-dialects of Arabic Using Support-Vector Machines","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"collecting-code-switched-data-from-social","title":"Collecting Code-Switched Data from Social Media","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coreference-resolution-in-freeling-40","title":"Coreference Resolution in FreeLing 4.0","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-parallel-language-resources-for","title":"Discovering Parallel Language Resources for Training MT Engines","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminating-between-similar-languages-on","title":"Discriminating between Similar Languages on Imbalanced Conversational Texts","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-asolved-problemsa-to-new-challenges-a","title":"From `Solved Problems' to New Challenges: A Report on LDC Activities","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"shami-a-corpus-of-levantine-arabic-dialects","title":"Shami: A Corpus of Levantine Arabic Dialects","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-normalization-infrastructure-that-scales","title":"Text Normalization Infrastructure that Scales to Hundreds of Language Varieties","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-french-algerian-code-switching-triggered","title":"The French-Algerian Code-Switching Triggered audio corpus (FACST)","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-language-technology-for-mikmaq","title":"Towards Language Technology for Mi'kmaq","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vast-a-corpus-of-video-annotation-for-speech","title":"VAST: A Corpus of Video Annotation for Speech Technologies","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/a-portuguese-native-language-identification","slug":"a-portuguese-native-language-identification","title":"A Portuguese Native Language Identification Dataset","date":"2018-04-30","arxiv_id":"1804.11346","repositories_listed":0,"syntology":null},{"url":null,"slug":"staircase-network-structural-language","title":"Staircase Network: structural language identification via hierarchical attentive units","date":"2018-04-30","arxiv_id":"1804.11067","repositories_listed":0,"syntology":null},{"url":"/paper/automated-essay-scoring-with-string-kernels","slug":"automated-essay-scoring-with-string-kernels","title":"Automated essay scoring with string kernels and word embeddings","date":"2018-04-21","arxiv_id":"1804.07954","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-language-identification-system-for","title":"Automatic Language Identification System for Hindi and Magahi","date":"2018-04-13","arxiv_id":"1804.05095","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-learnable-dictionary-encoding-layer","title":"A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification","date":"2018-04-02","arxiv_id":"1804.00385","repositories_listed":0,"syntology":null},{"url":null,"slug":"insights-into-end-to-end-learning-scheme-for","title":"Insights into End-to-End Learning Scheme for Language Identification","date":"2018-04-02","arxiv_id":"1804.00381","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-identification-of-closely-related","title":"Automatic Identification of Closely-related Indian Languages: Resources and Experiments","date":"2018-03-26","arxiv_id":"1803.09405","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-identification-of-bengali-english","title":"Language Identification of Bengali-English Code-Mixed data using Character & Phonetic based LSTM Models","date":"2018-03-10","arxiv_id":"1803.03859","repositories_listed":0,"syntology":null},{"url":null,"slug":"methods-for-spoken-language-identification","title":"Methods for Spoken Language Identification","date":"2017-12-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"curriculum-design-for-code-switching","title":"Curriculum Design for Code-switching: Experiments with Language Identification and Language Modeling with Deep Neural Networks","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-social-networks-to-improve-language","title":"Using Social Networks to Improve Language Variety Identification with Neural Networks","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dataset-and-classifier-for-recognizing","title":"A Dataset and Classifier for Recognizing Social Media English","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-based-native-language","title":"A deep-learning based native-language classification by using a latent semantic analysis for the NLI Shared Task 2017","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-report-on-the-2017-native-language","title":"A Report on the 2017 Native Language Identification Shared Task","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-shallow-neural-network-for-native-language","title":"A Shallow Neural Network for Native Language Identification with Character N-grams","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"all-that-is-english-may-be-hindi-enhancing-1","title":"All that is English may be Hindi: Enhancing language identification through automatic ranking of the likeliness of word borrowing in social media","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-dialectal-arabic-corpora","title":"Building Dialectal Arabic Corpora","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cic-fbk-approach-to-native-language","title":"CIC-FBK Approach to Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classifier-stacking-for-native-language","title":"Classifier Stacking for Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-textual-and-speech-features-in-the","title":"Combining Textual and Speech Features in the NLI Task Using State-of-the-Art Machine Learning Techniques","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-methods-for-native-language","title":"Ensemble Methods for Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-optimal-voting-in-native-language","title":"Exploring Optimal Voting in Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/fewer-features-perform-well-at-native","slug":"fewer-features-perform-well-at-native","title":"Fewer features perform well at Native Language Identification task","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-of-simple-models-for-native-language","title":"Fusion of Simple Models for Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-using-a","title":"Native Language Identification Using a Mixture of Character and Word N-grams","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-using-phonetic","title":"Native Language Identification using Phonetic Algorithms","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-networks-and-spelling-features-for","title":"Neural Networks and Spelling Features for Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stacked-sentence-document-classifier-approach","title":"Stacked Sentence-Document Classifier Approach for Improving Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-power-of-character-n-grams-in-native","title":"The Power of Character N-grams in Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vector-space-model-as-cognitive-space-for","title":"Vector Space Model as Cognitive Space for Text Classification","date":"2017-08-21","arxiv_id":"1708.06068","repositories_listed":0,"syntology":null},{"url":null,"slug":"lump-at-semeval-2017-task-1-towards-an","title":"Lump at SemEval-2017 Task 1: Towards an Interlingua Semantic Similarity","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-string-kernels-pass-the-test-of-time-in","title":"Can string kernels pass the test of time in Native Language Identification?","date":"2017-07-26","arxiv_id":"1707.08349","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-that-is-english-may-be-hindi-enhancing","title":"All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media","date":"2017-07-25","arxiv_id":"1707.08446","repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-on-text-and","title":"Native Language Identification on Text and Speech","date":"2017-07-22","arxiv_id":"1707.07182","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-language-identification","title":"Open-Set Language Identification","date":"2017-07-16","arxiv_id":"1707.04817","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-hashing-for-language-and-dialect","title":"Feature Hashing for Language and Dialect Identification","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-native-language-identification-by","title":"Improving Native Language Identification by Using Spelling Errors","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-dialectal-variability-for","title":"Incorporating Dialectal Variability for Socially Equitable Language Identification","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"racial-disparity-in-natural-language","title":"Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English","date":"2017-06-30","arxiv_id":"1707.00061","repositories_listed":0,"syntology":null},{"url":null,"slug":"phone-aware-neural-language-identification","title":"Phone-aware Neural Language Identification","date":"2017-05-09","arxiv_id":"1705.03152","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetic-temporal-neural-model-for-language","title":"Phonetic Temporal Neural Model for Language Identification","date":"2017-05-09","arxiv_id":"1705.03151","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-language-identification-methods","title":"Evaluation of language identification methods using 285 languages","date":"2017-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-with-learner-corpora-using-the-tle","title":"Learning with learner corpora: Using the TLE for native language identification","date":"2017-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-for-rhetorical-figure","title":"Machine Learning for Rhetorical Figure Detection: More Chiasmus with Less Annotation","date":"2017-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-code-switching-corpus-of-turkish-german","title":"A Code-Switching Corpus of Turkish-German Conversations","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-perplexity-based-method-for-similar","title":"A Perplexity-Based Method for Similar Languages Discrimination","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cluzh-at-vardial-gdi-2017-testing-a-variety","title":"CLUZH at VarDial GDI 2017: Testing a Variety of Machine Learning Tools for the Classification of Swiss German Dialects","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminating-between-similar-languages-with","title":"Discriminating between Similar Languages with Word-level Convolutional Neural Networks","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-heli-with-non-linear-mappings","title":"Evaluating HeLI with Non-Linear Mappings","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-lexical-and-syntactic-features-for","title":"Exploring Lexical and Syntactic Features for Language Variety Identification","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-vardial-evaluation-campaign","title":"Findings of the VarDial Evaluation Campaign 2017","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identification-of-languages-in-algerian","title":"Identification of Languages in Algerian Arabic Multilingual Documents","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-character-ngram-model-for-the","title":"Improving the Character Ngram Model for the DSL Task with BM25 Weighting and Less Frequently Used Feature Sets","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ta14bingen-system-in-vardial-2017-shared-task","title":"T\\\"ubingen system in VarDial 2017 shared task: experiments with language identification and cross-lingual parsing","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"twitter-language-identification-of-similar","title":"Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uriel-and-lang2vec-representing-languages-as","title":"URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"279d72978517e75e30d087ee54965cff0b87ef3600804f2a5a35bf8bc3505b34","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}