{"total":107,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2308.02976","title":"Spanish Pre-trained BERT Model and Evaluation Data","created":"2023-08-06","cited_by_count":81,"area":null},{"id":"2105.01735","title":"HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish","created":"2021-05-04","cited_by_count":51,"area":null},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29,"area":null},{"id":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2309.10931","title":"A Family of Pretrained Transformer Language Models for Russian","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2101.12175","title":"LOME: Large Ontology Multilingual Extraction","created":"2021-01-28","cited_by_count":23,"area":null},{"id":"2304.01666","title":"A Survey on Contextualised Semantic Shift Detection","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2408.02056","title":"MedSyn: LLM-based Synthetic Medical Text Generation Framework","created":"2024-08-04","cited_by_count":19,"area":null},{"id":"2311.13937","title":"Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification","created":"2023-11-23","cited_by_count":15,"area":null},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2106.07540","title":"Evaluating Various Tokenizers for Arabic Text Classification","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2105.09052","title":"Methods for Detoxification of Texts for the Russian Language","created":"2021-05-19","cited_by_count":13,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2108.13112","title":"NEREL: A Russian Dataset with Nested Named Entities, Relations and Events","created":"2021-08-30","cited_by_count":13,"area":null},{"id":"2109.07591","title":"On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation","created":"2021-09-15","cited_by_count":10,"area":null},{"id":"2201.06499","title":"RuMedBench: A Russian Medical Language Understanding Benchmark","created":"2022-01-17","cited_by_count":10,"area":null},{"id":"2210.11913","title":"NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entities","created":"2022-10-21","cited_by_count":10,"area":null},{"id":"2106.13553","title":"Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy","created":"2021-06-25","cited_by_count":9,"area":null},{"id":"2111.08634","title":"NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21","created":"2021-11-16","cited_by_count":8,"area":null},{"id":"2205.11159","title":"RuNNE-2022 Shared Task: Recognizing Nested Named Entities","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2209.07278","title":"\\'UFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2304.04190","title":"Team QUST at SemEval-2023 Task 3: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting Online News Genre, Framing and Persuasion Techniques","created":"2023-04-09","cited_by_count":8,"area":null},{"id":"2412.21140","title":"Facilitating large language model Russian adaptation with Learned Embedding Propagation","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2103.13799","title":"Bertinho: Galician BERT Representations","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2112.10553","title":"Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2103.05345","title":"Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2109.06327","title":"Evaluating Transferability of BERT Models on Uralic Languages","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2204.03951","title":"RuBioRoBERTa: a pre-trained biomedical language model for Russian language biomedical text mining","created":"2022-04-08","cited_by_count":6,"area":null},{"id":"2305.02215","title":"Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2106.07742","title":"Can BERT Dig It? -- Named Entity Recognition for Information Retrieval in the Archaeology Domain","created":"2021-06-14","cited_by_count":5,"area":null},{"id":"2303.09421","title":"SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2312.02598","title":"Impact of Tokenization on LLaMa Russian Adaptation","created":"2023-12-05","cited_by_count":5,"area":null},{"id":"2412.09203","title":"CleanComedy: Creating Friendly Humor through Generative Techniques","created":"2024-12-12","cited_by_count":5,"area":null},{"id":"2107.10614","title":"Evaluation of contextual embeddings on less-resourced languages","created":"2021-07-22","cited_by_count":4,"area":null},{"id":"2111.10097","title":"Lexicon-based Methods vs. BERT for Text Sentiment Analysis","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2206.09249","title":"RuArg-2022: Argument Mining Evaluation","created":"2022-06-18","cited_by_count":4,"area":null},{"id":"2209.12516","title":"End-to-end Multilingual Coreference Resolution with Mention Head Prediction","created":"2022-09-26","cited_by_count":4,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2403.17553","title":"RuBia: A Russian Language Bias Detection Dataset","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2509.14493","title":"Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2105.12530","title":"Deception detection in text and its relation to the cultural dimension of individualism/collectivism","created":"2021-05-26","cited_by_count":3,"area":null},{"id":"2106.14438","title":"Traditional Machine Learning and Deep Learning Models for Argumentation Mining in Russian Texts","created":"2021-06-28","cited_by_count":3,"area":null},{"id":"2206.07427","title":"Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task","created":"2022-06-15","cited_by_count":3,"area":null},{"id":"2208.10228","title":"Review of Natural Language Processing in Pharmacology","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2302.00407","title":"On the Role of Morphological Information for Contextual Lemmatization","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2306.05370","title":"Detecting Human Rights Violations on Social Media during Russia-Ukraine War","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2408.16893","title":"Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUD","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2410.17532","title":"Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2411.14896","title":"Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2501.02631","title":"Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian","created":"2025-01-05","cited_by_count":3,"area":null},{"id":"2507.02088","title":"McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2111.07148","title":"SocialBERT -- Transformers for Online SocialNetwork Language Modelling","created":"2021-11-13","cited_by_count":2,"area":null},{"id":"2201.10463","title":"Distantly supervised end-to-end medical entity extraction from electronic health records with human-level quality","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2410.07129","title":"Exploring Large Language Models for Detecting Mental Disorders","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2410.14074","title":"Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2508.16867","title":"QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments","created":"2025-08-23","cited_by_count":2,"area":null},{"id":"2509.25664","title":"QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2105.00981","title":"Russian News Clustering and Headline Selection Shared Task","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2105.01192","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2107.02499","title":"Transfer Learning for Improving Results on Russian Sentiment Datasets","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2110.02052","title":"Transfer Learning for Multi-lingual Tasks -- a Survey","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2111.10100","title":"Does BERT look at sentiment lexicon?","created":"2021-11-19","cited_by_count":1,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2204.13638","title":"Russian Texts Detoxification with Levenshtein Editing","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2206.09253","title":"Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods","created":"2022-06-18","cited_by_count":1,"area":null},{"id":"2209.14854","title":"TERMinator: A system for scientific texts processing","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2306.07797","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2310.04074","title":"Automatic Aspect Extraction from Scientific Texts","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2403.16968","title":"Evaluating Shortest Edit Script Methods for Contextual Lemmatization","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2409.10640","title":"Exploring Fine-tuned Generative Models for Keyphrase Selection: A Case Study for Russian","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2503.08696","title":"Multimodal Stock Price Prediction: A Case Study of the Russian Securities Market","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2603.24896","title":"LogSigma at SemEval-2026 Task 3: Uncertainty-Weighted Multitask Learning for Dimensional Aspect-Based Sentiment Analysis","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.04576","title":"Benchmarking POS Tagging for the Tajik Language: A Comparative Study of Neural Architectures on the TajPersParallel Corpus","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2609.01572","title":"From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2102.10958","title":"Bilingual Language Modeling, A transfer learning technique for Roman Urdu","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2104.14314","title":"MOROCCO: Model Resource Comparison Framework","created":"2021-04-29","cited_by_count":0,"area":null},{"id":"2106.01091","title":"belabBERT: a Dutch RoBERTa-based language model applied to psychiatric classification","created":"2021-06-02","cited_by_count":0,"area":null},{"id":"2106.10487","title":"Transformers for Headline Selection for Russian News Clusters","created":"2021-06-19","cited_by_count":0,"area":null},{"id":"2106.14434","title":"Current Landscape of the Russian Sentiment Corpora","created":"2021-06-28","cited_by_count":0,"area":null},{"id":"2111.04507","title":"Ontology-based question answering over corporate structured data","created":"2021-11-08","cited_by_count":0,"area":null},{"id":"2201.08598","title":"Taxonomy Enrichment with Text and Graph Vector Representations","created":"2022-01-21","cited_by_count":0,"area":null},{"id":"2201.09997","title":"Razmecheno: Named Entity Recognition from Digital Archive of Diaries \"Prozhito\"","created":"2022-01-24","cited_by_count":0,"area":null},{"id":"2202.06769","title":"Punctuation restoration in Swedish through fine-tuned KB-BERT","created":"2022-02-14","cited_by_count":0,"area":null},{"id":"2206.01137","title":"Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translation","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2206.01987","title":"Atypical lexical abbreviations identification in Russian medical texts","created":"2022-06-04","cited_by_count":0,"area":null},{"id":"2206.09251","title":"Argumentative Text Generation in Economic Domain","created":"2022-06-18","cited_by_count":0,"area":null},{"id":"2304.05336","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2305.13403","title":"GATology for Linguistics: What Syntactic Dependencies It Knows","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2309.14662","title":"Transformer-based classification of user queries for medical consultancy with respect to expert specialization","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2503.10233","title":"ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2505.17704","title":"SemSketches-2021: experimenting with the machine processing of the pilot semantic sketches corpus","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.14982","title":"Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2512.06586","title":"Adapting AlignScore Mertic for Factual Consistency Evaluation of Text in Russian: A Student Abstract","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2601.04211","title":"Qwerty AI: Explainable Automated Age Rating and Content Safety Assessment for Russian-Language Screenplays","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2604.03672","title":"AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services","created":"2026-04-04","cited_by_count":0,"area":null}],"next_cursor":"100"}