{"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/pos-tagging/papers/2","list_of":"/task/pos-tagging","task":"POS 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":2,"pages_in_order":6,"rows_per_page":100,"rows":[101,200],"of":523,"counts":{"archive_papers_tagged":523,"with_a_code_link":136,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":523,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/pos-tagging","prev":"/task/pos-tagging","next":"/task/pos-tagging/papers/3","papers":[{"url":"/paper/ufal-mrpipe-at-mrp-2019-udpipe-goes-semantic","slug":"ufal-mrpipe-at-mrp-2019-udpipe-goes-semantic","title":"ÚFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task","date":"2019-10-24","arxiv_id":"1910.11295","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-parsing-with-polyglot-training","slug":"cross-lingual-parsing-with-polyglot-training","title":"Cross-lingual Parsing with Polyglot Training and Multi-treebank Learning: A Faroese Case Study","date":"2019-10-17","arxiv_id":"1910.07938","repositories_listed":1,"syntology":null},{"url":"/paper/language-agnostic-syllabification-with-neural","slug":"language-agnostic-syllabification-with-neural","title":"Language-Agnostic Syllabification with Neural Sequence Labeling","date":"2019-09-29","arxiv_id":"1909.13362","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/augmenting-a-bilstm-tagger-with-a","slug":"augmenting-a-bilstm-tagger-with-a","title":"Augmenting a BiLSTM tagger with a Morphological Lexicon and a Lexical Category Identification Step","date":"2019-07-21","arxiv_id":"1907.09038","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-syntactic-transfer-through","slug":"cross-lingual-syntactic-transfer-through","title":"Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections","date":"2019-06-06","arxiv_id":"1906.02656","repositories_listed":1,"syntology":null},{"url":"/paper/bert-rediscovers-the-classical-nlp-pipeline","slug":"bert-rediscovers-the-classical-nlp-pipeline","title":"BERT Rediscovers the Classical NLP Pipeline","date":"2019-05-15","arxiv_id":"1905.05950","repositories_listed":1,"syntology":null},{"url":"/paper/a-grounded-unsupervised-universal-part-of","slug":"a-grounded-unsupervised-universal-part-of","title":"A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages","date":"2019-04-10","arxiv_id":"1904.05426","repositories_listed":1,"syntology":null},{"url":"/paper/universal-dependency-parsing-from-scratch","slug":"universal-dependency-parsing-from-scratch","title":"Universal Dependency Parsing from Scratch","date":"2019-01-29","arxiv_id":"1901.10457","repositories_listed":1,"syntology":null},{"url":"/paper/pd3-better-low-resource-cross-lingual","slug":"pd3-better-low-resource-cross-lingual","title":"PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection","date":"2018-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modeling-composite-labels-for-neural","slug":"modeling-composite-labels-for-neural","title":"Modeling Composite Labels for Neural Morphological Tagging","date":"2018-10-20","arxiv_id":"1810.08815","repositories_listed":1,"syntology":null},{"url":"/paper/toward-a-standardized-and-more-accurate","slug":"toward-a-standardized-and-more-accurate","title":"Toward a Standardized and More Accurate Indonesian Part-of-Speech Tagging","date":"2018-09-10","arxiv_id":"1809.03391","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-labeling-a-practical-approach","slug":"sequence-labeling-a-practical-approach","title":"Sequence Labeling: A Practical Approach","date":"2018-08-12","arxiv_id":"1808.03926","repositories_listed":1,"syntology":null},{"url":"/paper/an-improved-neural-network-model-for-joint","slug":"an-improved-neural-network-model-for-joint","title":"An improved neural network model for joint POS tagging and dependency parsing","date":"2018-07-11","arxiv_id":"1807.03955","repositories_listed":1,"syntology":null},{"url":"/paper/part-of-speech-tagging-on-an-endangered","slug":"part-of-speech-tagging-on-an-endangered","title":"Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource","date":"2018-06-11","arxiv_id":"1806.03757","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-graph-based-tag-parsing-with","slug":"end-to-end-graph-based-tag-parsing-with","title":"End-to-end Graph-based TAG Parsing with Neural Networks","date":"2018-04-18","arxiv_id":"1804.06610","repositories_listed":1,"syntology":null},{"url":"/paper/a-feature-rich-vietnamese-named-entity","slug":"a-feature-rich-vietnamese-named-entity","title":"A Feature-Rich Vietnamese Named-Entity Recognition Model","date":"2018-03-12","arxiv_id":"1803.04375","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-accuracy-of-pre-trained-word","slug":"improving-the-accuracy-of-pre-trained-word","title":"Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis","date":"2017-11-23","arxiv_id":"1711.08609","repositories_listed":1,"syntology":null},{"url":"/paper/from-word-segmentation-to-pos-tagging-for","slug":"from-word-segmentation-to-pos-tagging-for","title":"From Word Segmentation to POS Tagging for Vietnamese","date":"2017-11-14","arxiv_id":"1711.04951","repositories_listed":1,"syntology":null},{"url":"/paper/robust-multilingual-part-of-speech-tagging","slug":"robust-multilingual-part-of-speech-tagging","title":"Robust Multilingual Part-of-Speech Tagging via Adversarial Training","date":"2017-11-14","arxiv_id":"1711.04903","repositories_listed":1,"syntology":null},{"url":"/paper/replicability-analysis-for-natural-language","slug":"replicability-analysis-for-natural-language","title":"Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets","date":"2017-09-27","arxiv_id":"1709.09500","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-structured-prediction-with","slug":"semi-supervised-structured-prediction-with","title":"Semi-supervised Structured Prediction with Neural CRF Autoencoder","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/combining-discrete-and-neural-features-for","slug":"combining-discrete-and-neural-features-for","title":"Combining Discrete and Neural Features for Sequence Labeling","date":"2017-08-24","arxiv_id":"1708.07279","repositories_listed":1,"syntology":null},{"url":"/paper/nnvlp-a-neural-network-based-vietnamese","slug":"nnvlp-a-neural-network-based-vietnamese","title":"NNVLP: A Neural Network-Based Vietnamese Language Processing Toolkit","date":"2017-08-24","arxiv_id":"1708.07241","repositories_listed":1,"syntology":null},{"url":"/paper/to-normalize-or-not-to-normalize-the-impact","slug":"to-normalize-or-not-to-normalize-the-impact","title":"To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging","date":"2017-07-17","arxiv_id":"1707.05116","repositories_listed":1,"syntology":null},{"url":"/paper/a-non-projective-greedy-dependency-parser","slug":"a-non-projective-greedy-dependency-parser","title":"A non-projective greedy dependency parser with bidirectional LSTMs","date":"2017-07-11","arxiv_id":"1707.03228","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/character-based-joint-segmentation-and-pos","slug":"character-based-joint-segmentation-and-pos","title":"Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF","date":"2017-04-05","arxiv_id":"1704.01314","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/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/neural-relation-extraction-with-selective","slug":"neural-relation-extraction-with-selective","title":"Neural Relation Extraction with Selective Attention over Instances","date":"2016-08-01","arxiv_id":null,"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/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/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/exploiting-synergies-between-open-resources","slug":"exploiting-synergies-between-open-resources","title":"Exploiting Synergies Between Open Resources for German Dependency Parsing, POS-tagging, and Morphological Analysis","date":"2013-09-01","arxiv_id":null,"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":"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":"statistical-analysis-of-sentence-structures","title":"Statistical Analysis of Sentence Structures through ASCII, Lexical Alignment and PCA","date":"2025-03-13","arxiv_id":"2503.10470","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":"analyzing-the-effect-of-linguistic-similarity","title":"Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter","date":"2025-01-24","arxiv_id":"2501.14491","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":"babylms-for-isixhosa-data-efficient-language","title":"BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context","date":"2025-01-07","arxiv_id":"2501.03855","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":"limpeh-ga-li-gong-challenges-in-singlish","title":"Limpeh ga li gong: Challenges in Singlish Annotations","date":"2024-10-21","arxiv_id":"2410.16156","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-text-generation-in-joint-nlg-nlu","title":"Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques","date":"2024-10-17","arxiv_id":"2410.13498","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":"recipe-for-zero-shot-pos-tagging-is-it-useful","title":"Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?","date":"2024-10-14","arxiv_id":"2410.10576","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-intent-recognition-and-semantic-cache","title":"User Intent Recognition and Semantic Cache Optimization-Based Query Processing Framework using CFLIS and MGR-LAU","date":"2024-06-06","arxiv_id":"2406.04490","repositories_listed":0,"syntology":null},{"url":null,"slug":"tartunlp-sigtyp-2024-shared-task-adapting-xlm","title":"TartuNLP @ SIGTYP 2024 Shared Task: Adapting XLM-RoBERTa for Ancient and Historical Languages","date":"2024-04-19","arxiv_id":"2404.12845","repositories_listed":0,"syntology":null},{"url":null,"slug":"mrl-parsing-without-tears-the-case-of-hebrew","title":"MRL Parsing Without Tears: The Case of Hebrew","date":"2024-03-11","arxiv_id":"2403.06970","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-of-learning-curves-with-applications","title":"Modeling of learning curves with applications to pos tagging","date":"2024-02-04","arxiv_id":"2402.02515","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":"review-of-unsupervised-pos-tagging-and-its","title":"Review of Unsupervised POS Tagging and Its Implications on Language Acquisition","date":"2023-12-15","arxiv_id":"2312.10169","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":"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":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":"improved-pos-tagging-for-spontaneous-clinical","title":"Improved POS tagging for spontaneous, clinical speech using data augmentation","date":"2023-07-11","arxiv_id":"2307.05796","repositories_listed":0,"syntology":null},{"url":null,"slug":"vacaspati-a-diverse-corpus-of-bangla","title":"Vacaspati: A Diverse Corpus of Bangla Literature","date":"2023-07-11","arxiv_id":"2307.05083","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-grammatical-tagging-for-the-legal","title":"Towards Grammatical Tagging for the Legal Language of Cybersecurity","date":"2023-06-29","arxiv_id":"2306.17042","repositories_listed":0,"syntology":null},{"url":null,"slug":"latincy-synthetic-trained-pipelines-for-latin","title":"LatinCy: Synthetic Trained Pipelines for Latin NLP","date":"2023-05-07","arxiv_id":"2305.04365","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":"uzbektagger-the-rule-based-pos-tagger-for","title":"UzbekTagger: The rule-based POS tagger for Uzbek language","date":"2023-01-30","arxiv_id":"2301.12711","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-ambiguity-from-crowd-sequential","title":"Learning Ambiguity from Crowd Sequential Annotations","date":"2023-01-04","arxiv_id":"2301.01579","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":"towards-linguistically-informed-multi","title":"Towards Linguistically Informed Multi-Objective Pre-Training for Natural Language Inference","date":"2022-12-14","arxiv_id":"2212.07428","repositories_listed":0,"syntology":null},{"url":"/paper/large-pre-trained-models-with-extra-large","slug":"large-pre-trained-models-with-extra-large","title":"Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All","date":"2022-11-28","arxiv_id":"2211.15199","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-resource-methodological-bias-in-low","title":"High-Resource Methodological Bias in Low-Resource Investigations","date":"2022-11-14","arxiv_id":"2211.07534","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-performance-of-automatic-keyword","title":"Improving Performance of Automatic Keyword Extraction (AKE) Methods Using PoS-Tagging and Enhanced Semantic-Awareness","date":"2022-11-09","arxiv_id":"2211.05031","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-and-deep-learning-methods-with-manual","title":"Machine and Deep Learning Methods with Manual and Automatic Labelling for News Classification in Bangla Language","date":"2022-10-19","arxiv_id":"2210.10903","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-independent-approach-for","title":"Language-Independent Approach for Morphological Disambiguation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"udapter-typology-based-language-adapters-for","title":"UDapter: Typology-based Language Adapters for Multilingual Dependency Parsing and Sequence Labeling","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tarc-tunisian-arabish-corpus-first-complete","title":"TArC: Tunisian Arabish Corpus First complete release","date":"2022-07-11","arxiv_id":"2207.04796","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":"diversity-and-uncertainty-in-moderation-are-1","title":"”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sharp-search-based-adversarial-attack-for","title":"SHARP: Search-Based Adversarial Attack for Structured Prediction","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-and-uncertainty-in-moderation-are","title":"\"Diversity and Uncertainty in Moderation\" are the Key to Data Selection for Multilingual Few-shot Transfer","date":"2022-06-30","arxiv_id":"2206.15010","repositories_listed":0,"syntology":null},{"url":null,"slug":"dependency-parsing-with-backtracking-using","title":"Dependency Parsing with Backtracking using Deep Reinforcement Learning","date":"2022-06-28","arxiv_id":"2206.13914","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":"an-electra-model-for-latin-token-tagging","title":"An ELECTRA Model for Latin Token Tagging Tasks","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"analyse-automatique-de-lancien-armenien","title":"Analyse Automatique de l’Ancien Arménien. Évaluation d’une méthode hybride « dictionnaire » et « réseau de neurones » sur un Extrait de l’Adversus Haereses d’Irénée de Lyon","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":"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":"bertrade-using-contextual-embeddings-to-parse","title":"BERTrade: Using Contextual Embeddings to Parse Old French","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":"describing-language-variation-in-the","title":"Describing Language Variation in the Colophons of Armenian Manuscripts","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distant-reading-in-digital-humanities-case","title":"Distant Reading in Digital Humanities: Case Study on the Serbian Part of the ELTeC Collection","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hindiwsd-a-package-for-word-sense","title":"HindiWSD: A package for word sense disambiguation in Hinglish & Hindi","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"openkorpos-democratizing-korean-tokenization-1","title":"OpenKorPOS: Democratizing Korean Tokenization with Voting-Based Open Corpus Annotation","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-analysis-of-serbian-old-novels","title":"Sentiment Analysis of Serbian Old Novels","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"5953888f8680ca1b757ad07ec0c42e13e996d8f0fe735a0dc0079293f08bcbae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}