{"total":119,"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":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"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":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90,"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":"2307.03667","title":"Testing the Predictions of Surprisal Theory in 11 Languages","created":"2023-07-07","cited_by_count":77,"area":null},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68,"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":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2311.05640","title":"FinGPT: Large Generative Models for a Small Language","created":"2023-11-03","cited_by_count":49,"area":null},{"id":"2102.10684","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","created":"2021-02-21","cited_by_count":39,"area":null},{"id":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36,"area":null},{"id":"2105.11314","title":"RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model","created":"2021-05-24","cited_by_count":33,"area":null},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26,"area":null},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2301.09626","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","created":"2023-01-23","cited_by_count":26,"area":null},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2305.06721","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","created":"2023-05-11","cited_by_count":24,"area":null},{"id":"2103.13031","title":"Czert -- Czech BERT-like Model for Language Representation","created":"2021-03-24","cited_by_count":22,"area":null},{"id":"2104.06546","title":"Large-Scale Contextualised Language Modelling for Norwegian","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2304.10158","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","created":"2023-04-20","cited_by_count":19,"area":null},{"id":"2208.07864","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2402.12969","title":"Gl\\'orIA -- A Generative and Open Large Language Model for Portuguese","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2109.07348","title":"Cross-lingual Transfer of Monolingual Models","created":"2021-09-15","cited_by_count":14,"area":null},{"id":"2205.10517","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","created":"2022-05-21","cited_by_count":14,"area":null},{"id":"2210.14328","title":"Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models","created":"2022-10-25","cited_by_count":14,"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":"2201.05601","title":"A Warm Start and a Clean Crawled Corpus -- A Recipe for Good Language Models","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2205.08808","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","created":"2022-05-18","cited_by_count":13,"area":null},{"id":"2401.14373","title":"TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation","created":"2024-01-25","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2107.12930","title":"gaBERT -- an Irish Language Model","created":"2021-07-27","cited_by_count":12,"area":null},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2305.05480","title":"Effects of sub-word segmentation on performance of transformer language models","created":"2023-05-09","cited_by_count":12,"area":null},{"id":"2110.06273","title":"Sm{\\aa}prat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2103.13103","title":"Finnish Paraphrase Corpus","created":"2021-03-24","cited_by_count":10,"area":null},{"id":"2101.11363","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","created":"2021-01-27","cited_by_count":9,"area":null},{"id":"2411.11171","title":"LL\\\"aMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch","created":"2024-11-17","cited_by_count":9,"area":null},{"id":"2111.03800","title":"Finnish Dialect Identification: The Effect of Audio and Text","created":"2021-11-06","cited_by_count":8,"area":null},{"id":"2212.08390","title":"Lessons learned from the evaluation of Spanish Language Models","created":"2022-12-16","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":"2108.10640","title":"Are the Multilingual Models Better? Improving Czech Sentiment with Transformers","created":"2021-08-24","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":"2203.12906","title":"Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks","created":"2022-03-24","cited_by_count":7,"area":null},{"id":"2102.11278","title":"RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning","created":"2021-02-22","cited_by_count":6,"area":null},{"id":"2108.01139","title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","created":"2021-08-02","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":"2204.09145","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2212.09666","title":"MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code Completion","created":"2022-12-19","cited_by_count":6,"area":"moe"},{"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":"2408.15040","title":"A Survey of Large Language Models for European Languages","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2411.15734","title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","created":"2024-11-24","cited_by_count":6,"area":null},{"id":"2102.07396","title":"Beyond the English Web: Zero-Shot Cross-Lingual and Lightweight Monolingual Classification of Registers","created":"2021-02-15","cited_by_count":5,"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":"2108.09814","title":"UzBERT: pretraining a BERT model for Uzbek","created":"2021-08-22","cited_by_count":5,"area":null},{"id":"2109.11326","title":"The Current State of Finnish NLP","created":"2021-09-23","cited_by_count":5,"area":null},{"id":"2205.00965","title":"State-of-the-art in Open-domain Conversational AI: A Survey","created":"2022-05-02","cited_by_count":5,"area":null},{"id":"2403.20056","title":"Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2106.03389","title":"Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline","created":"2021-06-07","cited_by_count":4,"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":"2305.13641","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2104.11556","title":"Deep learning for sentence clustering in essay grading support","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2112.04329","title":"JABER and SABER: Junior and Senior Arabic BERt","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2205.07303","title":"TiBERT: Tibetan Pre-trained Language Model","created":"2022-05-15","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":"2107.02416","title":"Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings","created":"2021-07-06","cited_by_count":2,"area":null},{"id":"2109.05361","title":"COMBO: State-of-the-Art Morphosyntactic Analysis","created":"2021-09-11","cited_by_count":2,"area":null},{"id":"2112.04886","title":"Semantic Search as Extractive Paraphrase Span Detection","created":"2021-12-09","cited_by_count":2,"area":null},{"id":"2204.10621","title":"Out-of-Domain Evaluation of Finnish Dependency Parsing","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2206.04935","title":"Sort by Structure: Language Model Ranking as Dependency Probing","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2303.18121","title":"BERTino: an Italian DistilBERT model","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2305.16302","title":"Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages","created":"2023-05-25","cited_by_count":2,"area":"distill"},{"id":"2306.10419","title":"Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation","created":"2023-06-17","cited_by_count":2,"area":null},{"id":"2309.11165","title":"Assessment of Pre-Trained Models Across Languages and Grammars","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2309.11259","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2601.04469","title":"SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2105.02477","title":"Quantitative Evaluation of Alternative Translations in a Corpus of Highly Dissimilar Finnish Paraphrases","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2107.03809","title":"COMBO: a new module for EUD parsing","created":"2021-07-08","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":"2111.13138","title":"TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2204.03465","title":"BERTuit: Understanding Spanish language in Twitter through a native transformer","created":"2022-04-07","cited_by_count":1,"area":null},{"id":"2204.08083","title":"AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages","created":"2022-04-17","cited_by_count":1,"area":null},{"id":"2210.07523","title":"Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2211.13794","title":"Question Answering and Question Generation for Finnish","created":"2022-11-24","cited_by_count":1,"area":null},{"id":"2310.12766","title":"Transformer-based Entity Legal Form Classification","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2501.05963","title":"Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2510.20002","title":"Forging GEMs: Advancing Greek NLP through Quality-Based Corpus Curation","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2606.08451","title":"Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models","created":"2026-06-07","cited_by_count":1,"area":"alignment"},{"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":"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":"2112.00567","title":"DPRK-BERT: The Supreme Language Model","created":"2021-12-01","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":"2210.05619","title":"Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2210.06207","title":"SilverAlign: MT-Based Silver Data Algorithm For Evaluating Word Alignment","created":"2022-10-12","cited_by_count":0,"area":null}],"next_cursor":"100"}