{"total":90,"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":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2301.13771","title":"The Touch\\'e23-ValueEval Dataset for Identifying Human Values behind Arguments","created":"2023-01-31","cited_by_count":28,"area":null},{"id":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"area":null},{"id":"2104.06546","title":"Large-Scale Contextualised Language Modelling for Norwegian","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2202.06219","title":"PQuAD: A Persian Question Answering Dataset","created":"2022-02-13","cited_by_count":14,"area":null},{"id":"2107.12930","title":"gaBERT -- an Irish Language Model","created":"2021-07-27","cited_by_count":12,"area":null},{"id":"2104.07613","title":"SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian","created":"2021-04-15","cited_by_count":10,"area":null},{"id":"2402.06617","title":"FaBERT: Pre-training BERT on Persian Blogs","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2502.11571","title":"FaMTEB: Massive Text Embedding Benchmark in Persian Language","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2207.11808","title":"ArmanEmo: A Persian Dataset for Text-based Emotion Detection","created":"2022-07-24","cited_by_count":9,"area":null},{"id":"2203.03216","title":"USTC-NELSLIP at SemEval-2022 Task 11: Gazetteer-Adapted Integration Network for Multilingual Complex Named Entity Recognition","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2109.14934","title":"Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2401.06466","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","created":"2024-01-12","cited_by_count":7,"area":null},{"id":"2407.16382","title":"TookaBERT: A Step Forward for Persian NLU","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2211.14402","title":"An Analysis of Social Biases Present in BERT Variants Across Multiple Languages","created":"2022-11-25","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":"2112.13238","title":"PerCQA: Persian Community Question Answering Dataset","created":"2021-12-25","cited_by_count":5,"area":null},{"id":"2208.13486","title":"naab: A ready-to-use plug-and-play corpus for Farsi","created":"2022-08-29","cited_by_count":5,"area":null},{"id":"2208.14657","title":"EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2312.04362","title":"PCoQA: Persian Conversational Question Answering Dataset","created":"2023-12-07","cited_by_count":5,"area":null},{"id":"2305.02426","title":"evaluating bert and parsbert for analyzing persian advertisement data","created":"2023-05-03","cited_by_count":4,"area":null},{"id":"2505.16000","title":"Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2103.02636","title":"A Novel Context-Aware Multimodal Framework for Persian Sentiment Analysis","created":"2021-03-03","cited_by_count":3,"area":null},{"id":"2111.02188","title":"BERT-DRE: BERT with Deep Recursive Encoder for Natural Language Sentence Matching","created":"2021-11-03","cited_by_count":3,"area":null},{"id":"2204.09292","title":"Towards Arabic Sentence Simplification via Classification and Generative Approaches","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2205.07220","title":"Adaptive Prompt Learning-based Few-Shot Sentiment Analysis","created":"2022-05-15","cited_by_count":3,"area":null},{"id":"2405.06760","title":"Opportunities for Persian Digital Humanities Research with Artificial Intelligence Language Models; Case Study: Forough Farrokhzad","created":"2024-05-10","cited_by_count":3,"area":null},{"id":"2506.00250","title":"PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2510.10774","title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis","created":"2025-10-12","cited_by_count":3,"area":null},{"id":"2109.04098","title":"ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2110.05133","title":"Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2202.10879","title":"Evaluating Persian Tokenizers","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2211.08029","title":"Persian Emotion Detection using ParsBERT and Imbalanced Data Handling Approaches","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2303.04134","title":"A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2306.16268","title":"Emotion Analysis of Tweets Banning Education in Afghanistan","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2310.09362","title":"From Words and Exercises to Wellness: Farsi Chatbot for Self-Attachment Technique","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2401.00811","title":"PerSHOP -- A Persian dataset for shopping dialogue systems modeling","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2407.11186","title":"Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2407.19173","title":"FarSSiBERT: A Novel Transformer-based Model for Semantic Similarity Measurement of Persian Social Networks Informal Texts","created":"2024-07-27","cited_by_count":2,"area":null},{"id":"2505.08435","title":"Hakim: Farsi Text Embedding Model","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2107.01987","title":"Contradiction Detection in Persian Text","created":"2021-07-05","cited_by_count":1,"area":null},{"id":"2110.09086","title":"ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2201.06573","title":"PerPaDa: A Persian Paraphrase Dataset based on Implicit Crowdsourcing Data Collection","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2302.09611","title":"Exploring the Potential of Machine Translation for Generating Named Entity Datasets: A Case Study between Persian and English","created":"2023-02-19","cited_by_count":1,"area":null},{"id":"2304.11664","title":"IslamicPCQA: A Dataset for Persian Multi-hop Complex Question Answering in Islamic Text Resources","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2306.10339","title":"Persian Semantic Role Labeling Using Transfer Learning and BERT-Based Models","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2307.03764","title":"For Women, Life, Freedom: A Participatory AI-Based Social Web Analysis of a Watershed Moment in Iran's Gender Struggles","created":"2023-07-07","cited_by_count":1,"area":null},{"id":"2407.14789","title":"PERCORE: A Deep Learning-Based Framework for Persian Spelling Correction with Phonetic Analysis","created":"2024-07-20","cited_by_count":1,"area":null},{"id":"2508.05628","title":"H-Net++: Hierarchical Dynamic Chunking for Tokenizer-Free Language Modelling in Morphologically-Rich Languages","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2601.20592","title":"A Computational Approach to Language Contact -- A Case Study of Persian","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2603.05314","title":"PersianPunc: A Large-Scale Dataset and BERT-Based Approach for Persian Punctuation Restoration","created":"2026-03-05","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":"2106.14165","title":"Persian Causality Corpus (PerCause) and the Causality Detection Benchmark","created":"2021-06-27","cited_by_count":0,"area":null},{"id":"2107.02040","title":"A Knowledge-based Approach for Answering Complex Questions in Persian","created":"2021-07-05","cited_by_count":0,"area":null},{"id":"2203.15323","title":"Improving Persian Relation Extraction Models by Data Augmentation","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2205.08755","title":"Persian Natural Language Inference: A Meta-learning approach","created":"2022-05-18","cited_by_count":0,"area":null},{"id":"2302.04511","title":"A Large-Scale Analysis of Persian Tweets Regarding Covid-19 Vaccination","created":"2023-02-09","cited_by_count":0,"area":null},{"id":"2305.03201","title":"Enhancing Pashto Text Classification using Language Processing Techniques for Single And Multi-Label Analysis","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2305.03737","title":"Tuning Traditional Language Processing Approaches for Pashto Text Classification","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2306.14067","title":"UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2307.07740","title":"Political Sentiment Analysis of Persian Tweets Using CNN-LSTM Model","created":"2023-07-15","cited_by_count":0,"area":null},{"id":"2307.16082","title":"EnrichEvent: Enriching Social Data with Contextual Information for Emerging Event Extraction","created":"2023-07-29","cited_by_count":0,"area":null},{"id":"2310.00572","title":"Colloquial Persian POS (CPPOS) Corpus: A Novel Corpus for Colloquial Persian Part of Speech Tagging","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2311.00143","title":"Two-Stage Classifier for Campaign Negativity Detection using Axis Embeddings: A Case Study on Tweets of Political Users during 2021 Presidential Election in Iran","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2403.06023","title":"Persian Slang Text Conversion to Formal and Deep Learning of Persian Short Texts on Social Media for Sentiment Classification","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2404.02335","title":"Multi-BERT: Leveraging Adapters and Prompt Tuning for Low-Resource Multi-Domain Adaptation","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2404.05540","title":"OPSD: an Offensive Persian Social media Dataset and its baseline evaluations","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2404.13079","title":"Relational Graph Convolutional Networks for Sentiment Analysis","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2405.10714","title":"Persian Pronoun Resolution: Leveraging Neural Networks and Language Models","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2407.17383","title":"A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2408.03622","title":"Improving the quality of Persian clinical text with a novel spelling correction system","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2412.20212","title":"Building a Rich Dataset to Empower the Persian Question Answering Systems","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2504.10662","title":"Emotion Alignment: Discovering the Gap Between Social Media and Real-World Sentiments in Persian Tweets and Images","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2505.20571","title":"Emotion Classification In-Context in Spanish","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.18762","title":"The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2510.04291","title":"PABSA: Hybrid Framework for Persian Aspect-Based Sentiment Analysis","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.15134","title":"FarsiMCQGen: a Persian Multiple-choice Question Generation Framework","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2601.17664","title":"UrduLM: A Resource-Efficient Monolingual Urdu Language Model","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.12778","title":"Aspect-Based Sentiment Analysis for Future Tourism Experiences: A BERT-MoE Framework for Persian User Reviews","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.19333","title":"PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2602.22827","title":"TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.22977","title":"DariMis: Harm-Aware Modeling for Dari Misinformation Detection on YouTube","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.27233","title":"Structural Stress and Learned Helplessness in Afghanistan: A Multi-Layer Analysis of the AFSTRESS Dari Corpus","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.21370","title":"MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.20089","title":"IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.24698","title":"The Annotation Bottleneck in Persian Text NLP: Persian as an Annotation-Scarce Language","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.00958","title":"PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.16393","title":"ParsHate: A Benchmark Dataset for Hate and Target Detection in Persian","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}