{"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/part-of-speech-tagging/papers/3","list_of":"/task/part-of-speech-tagging","task":"Part-Of-Speech Tagging","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":3,"pages_in_order":10,"rows_per_page":100,"rows":[201,300],"of":990,"counts":{"archive_papers_tagged":990,"with_a_code_link":228,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":990,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":24,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":24,"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/part-of-speech-tagging","prev":"/task/part-of-speech-tagging/papers/2","next":"/task/part-of-speech-tagging/papers/4","papers":[{"url":"/paper/abstract-meaning-representation-parsing-using","slug":"abstract-meaning-representation-parsing-using","title":"Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/aggregating-and-predicting-sequence-labels","slug":"aggregating-and-predicting-sequence-labels","title":"Aggregating and Predicting Sequence Labels from Crowd Annotations","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/esteem-a-novel-framework-for-qualitatively","slug":"esteem-a-novel-framework-for-qualitatively","title":"ESTEEM: A Novel Framework for Qualitatively Evaluating and Visualizing Spatiotemporal Embeddings in Social Media","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-general-purpose-tagger-with-convolutional","slug":"a-general-purpose-tagger-with-convolutional","title":"A General-Purpose Tagger with Convolutional Neural Networks","date":"2017-06-06","arxiv_id":"1706.01723","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-neural-network-model-for-joint-pos","slug":"a-novel-neural-network-model-for-joint-pos","title":"A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing","date":"2017-05-16","arxiv_id":"1705.05952","repositories_listed":1,"syntology":null},{"url":"/paper/a-tidy-data-model-for-natural-language","slug":"a-tidy-data-model-for-natural-language","title":"A Tidy Data Model for Natural Language Processing using cleanNLP","date":"2017-03-27","arxiv_id":"1703.09570","repositories_listed":1,"syntology":null},{"url":"/paper/smpost-parts-of-speech-tagger-for-code-mixed","slug":"smpost-parts-of-speech-tagger-for-code-mixed","title":"SMPOST: Parts of Speech Tagger for Code-Mixed Indic Social Media Text","date":"2017-02-01","arxiv_id":"1702.00167","repositories_listed":1,"syntology":null},{"url":"/paper/better-call-saul-flexible-programming-for","slug":"better-call-saul-flexible-programming-for","title":"Better call Saul: Flexible Programming for Learning and Inference in NLP","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/biomedlat-corpus-annotation-of-the-lexical","slug":"biomedlat-corpus-annotation-of-the-lexical","title":"BioMedLAT Corpus: Annotation of the Lexical Answer Type for Biomedical Questions","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/speed-accuracy-tradeoffs-in-tagging-with","slug":"speed-accuracy-tradeoffs-in-tagging-with","title":"Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity","date":"2016-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantic-tagging-with-deep-residual-networks","slug":"semantic-tagging-with-deep-residual-networks","title":"Semantic Tagging with Deep Residual Networks","date":"2016-09-22","arxiv_id":"1609.07053","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/semantic-tagging-with-deep-residual-networks#ran","syntology_url":"https://syntology.ai/paper/1609.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07053"}},"official":{"repos":["bjerva/semantic-tagging"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/read-tag-and-parse-all-at-once-or-fully","slug":"read-tag-and-parse-all-at-once-or-fully","title":"Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing","date":"2016-09-12","arxiv_id":"1609.03441","repositories_listed":1,"syntology":null},{"url":"/paper/bangla-parts-of-speech-tagging-using-bangla","slug":"bangla-parts-of-speech-tagging-using-bangla","title":"Bangla Parts-of-Speech Tagging using Bangla Stemmer and Rule based Analyzer","date":"2016-06-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/urdu-summary-corpus","slug":"urdu-summary-corpus","title":"Urdu Summary Corpus","date":"2016-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/globally-normalized-transition-based-neural","slug":"globally-normalized-transition-based-neural","title":"Globally Normalized Transition-Based Neural Networks","date":"2016-03-19","arxiv_id":"1603.06042","repositories_listed":1,"syntology":null},{"url":"/paper/integrated-sequence-tagging-for-medieval","slug":"integrated-sequence-tagging-for-medieval","title":"Integrated Sequence Tagging for Medieval Latin Using Deep Representation Learning","date":"2016-03-04","arxiv_id":"1603.01597","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-part-of-speech-tagging-with","slug":"unsupervised-part-of-speech-tagging-with","title":"Unsupervised Part-Of-Speech Tagging with Anchor Hidden Markov Models","date":"2016-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-meta-embeddings-by-using-ensembles","slug":"learning-meta-embeddings-by-using-ensembles","title":"Learning Meta-Embeddings by Using Ensembles of Embedding Sets","date":"2015-08-18","arxiv_id":"1508.04257","repositories_listed":1,"syntology":null},{"url":"/paper/finding-function-in-form-compositional-1","slug":"finding-function-in-form-compositional-1","title":"Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation","date":"2015-08-09","arxiv_id":"1508.02096","repositories_listed":1,"syntology":null},{"url":"/paper/minority-language-twitter-part-of-speech","slug":"minority-language-twitter-part-of-speech","title":"Minority Language Twitter: Part-of-Speech Tagging and Analysis of Irish Tweets","date":"2015-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/twotoo-simple-adaptations-of-word2vec-for","slug":"twotoo-simple-adaptations-of-word2vec-for","title":"Two/Too Simple Adaptations of Word2Vec for Syntax Problems","date":"2015-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-robust-transformation-based-learning","slug":"a-robust-transformation-based-learning","title":"A Robust Transformation-Based Learning Approach Using Ripple Down Rules for Part-of-Speech Tagging","date":"2014-12-12","arxiv_id":"1412.4021","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-client-side-chinesejapanese","slug":"lightweight-client-side-chinesejapanese","title":"Lightweight Client-Side Chinese/Japanese Morphological Analyzer Based on Online Learning","date":"2014-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-stanford-corenlp-natural-language","slug":"the-stanford-corenlp-natural-language","title":"The Stanford CoreNLP Natural Language Processing Toolkit","date":"2014-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/twitie-an-open-source-information-extraction","slug":"twitie-an-open-source-information-extraction","title":"TwitIE: An Open-Source Information Extraction Pipeline for Microblog Text","date":"2013-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chinese-parsing-exploiting-characters","slug":"chinese-parsing-exploiting-characters","title":"Chinese Parsing Exploiting Characters","date":"2013-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-recognition-in-tweets-an","slug":"named-entity-recognition-in-tweets-an","title":"Named Entity Recognition in Tweets: An Experimental Study","date":"2011-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mbt-a-memory-based-part-of-speech-tagger","slug":"mbt-a-memory-based-part-of-speech-tagger","title":"MBT: A Memory-Based Part of Speech Tagger-Generator","date":"1996-07-11","arxiv_id":"cmp-lg/9607012","repositories_listed":1,"syntology":null},{"url":null,"slug":"fillm-a-filipino-optimized-large-language","title":"FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)","date":"2025-05-25","arxiv_id":"2505.18995","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-multilingual-encoder-language-model","title":"On Multilingual Encoder Language Model Compression for Low-Resource Languages","date":"2025-05-22","arxiv_id":"2505.16956","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundations-and-evaluations-in-nlp","title":"Foundations and Evaluations in NLP","date":"2025-04-02","arxiv_id":"2504.01342","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":"a-comparative-analysis-of-word-segmentation","title":"A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950","date":"2025-03-25","arxiv_id":"2503.19844","repositories_listed":0,"syntology":null},{"url":null,"slug":"untangling-the-influence-of-typology-data-and","title":"Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging","date":"2025-03-25","arxiv_id":"2503.19979","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-study-of-zero-shot-cross-lingual","title":"Comparative Study of Zero-Shot Cross-Lingual Transfer for Bodo POS and NER Tagging Using Gemini 2.0 Flash Thinking Experimental Model","date":"2025-03-06","arxiv_id":"2503.04405","repositories_listed":0,"syntology":null},{"url":null,"slug":"author-specific-linguistic-patterns-unveiled","title":"Author-Specific Linguistic Patterns Unveiled: A Deep Learning Study on Word Class Distributions","date":"2025-01-17","arxiv_id":"2501.10072","repositories_listed":0,"syntology":null},{"url":null,"slug":"bbpos-bert-based-part-of-speech-tagging-for","title":"BBPOS: BERT-based Part-of-Speech Tagging for Uzbek","date":"2025-01-17","arxiv_id":"2501.10107","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-foundations-for-natural-language","title":"Building Foundations for Natural Language Processing of Historical Turkish: Resources and Models","date":"2025-01-08","arxiv_id":"2501.04828","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-thorough-investigation-into-the-application","title":"A Thorough Investigation into the Application of Deep CNN for Enhancing Natural Language Processing Capabilities","date":"2024-12-20","arxiv_id":"2412.15900","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-pixel-language-models-on-non","title":"Evaluating Pixel Language Models on Non-Standardized Languages","date":"2024-12-12","arxiv_id":"2412.09084","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-assist-with-ambiguity-a-quantitative","title":"Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation","date":"2024-11-27","arxiv_id":"2411.18337","repositories_listed":0,"syntology":null},{"url":null,"slug":"sinatools-open-source-toolkit-for-arabic","title":"SinaTools: Open Source Toolkit for Arabic Natural Language Processing","date":"2024-11-03","arxiv_id":"2411.01523","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-transfer-learning-for-deep-nlp","title":"Exploring transfer learning for Deep NLP systems on rarely annotated languages","date":"2024-10-15","arxiv_id":"2410.12879","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-visual-information-in-chinese","title":"The Impact of Visual Information in Chinese Characters: Evaluating Large Models' Ability to Recognize and Utilize Radicals","date":"2024-10-11","arxiv_id":"2410.09013","repositories_listed":0,"syntology":null},{"url":null,"slug":"menakbert-hebrew-diacriticizer","title":"MenakBERT -- Hebrew Diacriticizer","date":"2024-10-03","arxiv_id":"2410.02417","repositories_listed":0,"syntology":null},{"url":null,"slug":"efontes-part-of-speech-tagging-and","title":"eFontes. Part of Speech Tagging and Lemmatization of Medieval Latin Texts.A Cross-Genre Survey","date":"2024-06-29","arxiv_id":"2407.00418","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-orthographic-variation-in-occitan-s","title":"Modeling Orthographic Variation in Occitan's Dialects","date":"2024-04-30","arxiv_id":"2404.19315","repositories_listed":0,"syntology":null},{"url":null,"slug":"holmes-benchmark-the-linguistic-competence-of","title":"Holmes: A Benchmark to Assess the Linguistic Competence of Language Models","date":"2024-04-29","arxiv_id":"2404.18923","repositories_listed":0,"syntology":null},{"url":null,"slug":"prefix-text-as-a-yarn-eliciting-non-english","title":"Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model","date":"2024-04-25","arxiv_id":"2404.16766","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-morphology-based-investigation-of","title":"A Morphology-Based Investigation of Positional Encodings","date":"2024-04-06","arxiv_id":"2404.04530","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-comparison-of-translationese-in-machine","title":"The Comparison of Translationese in Machine Translation and Human Transation in terms of Translation Relations","date":"2024-03-27","arxiv_id":"2404.08661","repositories_listed":0,"syntology":null},{"url":null,"slug":"zaebuc-spoken-a-multilingual-multidialectal","title":"ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus","date":"2024-03-27","arxiv_id":"2403.18182","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlpre-a-revised-approach-towards-language","title":"NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems","date":"2024-03-07","arxiv_id":"2403.04507","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-generation-of-multiple-choice-cloze","title":"Automated Generation of Multiple-Choice Cloze Questions for Assessing English Vocabulary Using GPT-turbo 3.5","date":"2024-03-04","arxiv_id":"2403.02078","repositories_listed":0,"syntology":null},{"url":null,"slug":"decomposed-prompting-unveiling-multilingual","title":"Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models","date":"2024-02-28","arxiv_id":"2402.18397","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effective-incorporating-heterogeneous","title":"An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling","date":"2024-02-21","arxiv_id":"2402.13534","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-view-of-the-biases-of","title":"A Comprehensive View of the Biases of Toxicity and Sentiment Analysis Methods Towards Utterances with African American English Expressions","date":"2024-01-23","arxiv_id":"2401.12720","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-resource-cross-lingual-part-of-speech","title":"Zero Resource Cross-Lingual Part Of Speech Tagging","date":"2024-01-11","arxiv_id":"2401.05727","repositories_listed":0,"syntology":null},{"url":null,"slug":"part-of-speech-tagger-for-bodo-language-using","title":"Part-of-Speech Tagger for Bodo Language using Deep Learning approach","date":"2024-01-06","arxiv_id":"2401.03175","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-bert-based-chinese-spelling-check-model","title":"Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Model","date":"2023-12-27","arxiv_id":"2312.16623","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-planetary-names-in-astronomy","title":"Identifying Planetary Names in Astronomy Papers: A Multi-Step Approach","date":"2023-12-14","arxiv_id":"2312.08579","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenty-a-python-library-for-structured-text","title":"Augmenty: A Python Library for Structured Text Augmentation","date":"2023-12-09","arxiv_id":"2312.05520","repositories_listed":0,"syntology":null},{"url":null,"slug":"bit-cipher-a-simple-yet-powerful-word","title":"Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models","date":"2023-11-18","arxiv_id":"2311.11012","repositories_listed":0,"syntology":null},{"url":"/paper/explainable-identification-of-hate-speech","slug":"explainable-identification-of-hate-speech","title":"Explainable Identification of Hate Speech towards Islam using Graph Neural Networks","date":"2023-11-02","arxiv_id":"2311.04916","repositories_listed":0,"syntology":null},{"url":null,"slug":"colloquial-persian-pos-cppos-corpus-a-novel","title":"Colloquial Persian POS (CPPOS) Corpus: A Novel Corpus for Colloquial Persian Part of Speech Tagging","date":"2023-10-01","arxiv_id":"2310.00572","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-using-lexical","title":"Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data","date":"2023-07-14","arxiv_id":"2307.10210","repositories_listed":0,"syntology":null},{"url":null,"slug":"gujibert-and-gujigpt-construction-of","title":"GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts","date":"2023-07-11","arxiv_id":"2307.05354","repositories_listed":0,"syntology":null},{"url":null,"slug":"pushing-the-limits-of-chatgpt-on-nlp-tasks","title":"Pushing the Limits of ChatGPT on NLP Tasks","date":"2023-06-16","arxiv_id":"2306.09719","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-deep-syntactic-and-semantic","title":"Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCN","date":"2023-06-03","arxiv_id":"2306.02078","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-french-language-modeling-with","title":"Data-Efficient French Language Modeling with CamemBERTa","date":"2023-06-02","arxiv_id":"2306.01497","repositories_listed":0,"syntology":null},{"url":null,"slug":"sejarah-dan-perkembangan-teknik-natural","title":"Sejarah dan Perkembangan Teknik Natural Language Processing (NLP) Bahasa Indonesia: Tinjauan tentang sejarah, perkembangan teknologi, dan aplikasi NLP dalam bahasa Indonesia","date":"2023-03-28","arxiv_id":"2304.02746","repositories_listed":0,"syntology":null},{"url":null,"slug":"aco-tagger-a-novel-method-for-part-of-speech","title":"ACO-tagger: A Novel Method for Part-of-Speech Tagging using Ant Colony Optimization","date":"2023-03-27","arxiv_id":"2303.16760","repositories_listed":0,"syntology":null},{"url":null,"slug":"assorted-archetypal-and-annotated-two-million","title":"Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning","date":"2023-03-27","arxiv_id":"2303.16778","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-generation-of-multiple-choice","title":"Automatic Generation of Multiple-Choice Questions","date":"2023-03-25","arxiv_id":"2303.14576","repositories_listed":0,"syntology":null},{"url":null,"slug":"aspos-assamese-part-of-speech-tagger-using","title":"AsPOS: Assamese Part of Speech Tagger using Deep Learning Approach","date":"2022-12-14","arxiv_id":"2212.07043","repositories_listed":0,"syntology":null},{"url":null,"slug":"searching-for-discriminative-words-in","title":"Searching for Discriminative Words in Multidimensional Continuous Feature Space","date":"2022-11-26","arxiv_id":"2211.14631","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-language-models-for-linguistic","title":"Prompting Language Models for Linguistic Structure","date":"2022-11-15","arxiv_id":"2211.07830","repositories_listed":0,"syntology":null},{"url":null,"slug":"multifaceted-assessments-of-traditional","title":"Multifaceted Assessments of Traditional Chinese Word Segmentation Tool on Large Corpora","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kencorpus-a-kenyan-language-corpus-of-swahili","title":"Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks","date":"2022-08-25","arxiv_id":"2208.12081","repositories_listed":0,"syntology":null},{"url":null,"slug":"part-of-speech-tagging-of-odia-language-using","title":"Part-of-Speech Tagging of Odia Language Using statistical and Deep Learning-Based Approaches","date":"2022-07-07","arxiv_id":"2207.03256","repositories_listed":0,"syntology":null},{"url":"/paper/sequence-alignment-ensemble-with-a-single","slug":"sequence-alignment-ensemble-with-a-single","title":"Sequence Alignment Ensemble with a Single Neural Network for Sequence Labeling","date":"2022-07-07","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-experimental-investigation-of-part-of","title":"An Experimental Investigation of Part-Of-Speech Taggers for Vietnamese","date":"2022-06-14","arxiv_id":"2206.06992","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-framework-for-ancient-chinese-ws-and","title":"A Joint Framework for Ancient Chinese WS and POS Tagging Based on Adversarial Ensemble Learning","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-warm-start-and-a-clean-crawled-corpus-a-1","title":"A Warm Start and a Clean Crawled Corpus - A Recipe for Good Language Models","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ancient-chinese-word-segmentation-and-part-of","title":"Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Data Augmentation","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"annotating-particles-in-multiword-expressions","title":"Annotating “Particles” in Multiword Expressions in te reo Māori for a Part-of-Speech Tagger","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-word-segmentation-and-part-of","title":"Automatic Word Segmentation and Part-of-Speech Tagging of Ancient Chinese Based on BERT Model","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-4ever-evahan-2022-ancient-chinese-word","title":"BERT 4EVER@EvaHan 2022: Ancient Chinese Word Segmentation and Part-of-Speech Tagging Based on Adversarial Learning and Continual Pre-training","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"construction-of-segmentation-and-part-of","title":"Construction of Segmentation and Part of Speech Annotation Model in Ancient Chinese","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-low-resource-word","title":"Data Augmentation for Low-resource Word Segmentation and POS Tagging of Ancient Chinese Texts","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"glyph-features-matter-a-multimodal-solution","title":"Glyph Features Matter: A Multimodal Solution for EvaHan in LT4HALA2022","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-sub-label-dependencies-in-code","title":"Leveraging Sub Label Dependencies in Code Mixed Indian Languages for Part-Of-Speech Tagging using Conditional Random Fields.","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-of-the-evalatin-2022-evaluation","title":"Overview of the EvaLatin 2022 Evaluation Campaign","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-and-evaluating-transformer-based","title":"Pre-training and Evaluating Transformer-based Language Models for Icelandic","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pycantonese-cantonese-linguistics-and-nlp-in","title":"PyCantonese: Cantonese Linguistics and NLP in Python","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-tagging-system-with-roberta-for","title":"Simple Tagging System with RoBERTa for Ancient Chinese","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-part-of-speech-tagging-and","title":"Transformer-based Part-of-Speech Tagging and Lemmatization for Latin","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zaebuc-an-annotated-arabic-english-bilingual","title":"ZAEBUC: An Annotated Arabic-English Bilingual Writer Corpus","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sketching-a-linguistically-driven-reasoning","title":"Sketching a Linguistically-Driven Reasoning Dialog Model for Social Talk","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fine-grained-classification-of","title":"Towards Fine-grained Classification of Climate Change related Social Media Text","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"14647a18932568490dbe02fce4aa05cf9384421449586496eb20ecf82c34c28e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}