{"total":37,"rows":[{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"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":"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":"2104.14694","title":"Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses","created":"2021-04-29","cited_by_count":39,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2104.06546","title":"Large-Scale Contextualised Language Modelling for Norwegian","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2109.15298","title":"Multi-granular Legal Topic Classification on Greek Legislation","created":"2021-09-30","cited_by_count":15,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2206.04510","title":"SsciBERT: A Pre-trained Language Model for Social Science Texts","created":"2022-06-09","cited_by_count":12,"area":null},{"id":"2109.15254","title":"SlovakBERT: Slovak Masked Language Model","created":"2021-09-30","cited_by_count":11,"area":null},{"id":"2305.13698","title":"Exploring Large Language Models for Classical Philology","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2304.00869","title":"GreekBART: The First Pretrained Greek Sequence-to-Sequence Model","created":"2023-04-03","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":"2410.24140","title":"Don't Touch My Diacritics","created":"2024-10-31","cited_by_count":7,"area":null},{"id":"2105.01180","title":"Scalar Adjective Identification and Multilingual Ranking","created":"2021-05-03","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":"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":"2408.15040","title":"A Survey of Large Language Models for European Languages","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2604.24470","title":"Zero-shot Large Language Models for Automatic Readability Assessment","created":"2026-04-27","cited_by_count":3,"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":"2208.01912","title":"Cross-Lingual Knowledge Transfer for Clinical Phenotyping","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2311.07767","title":"GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2506.08907","title":"Dialect Normalization using Large Language Models and Morphological Rules","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2111.03913","title":"Linguistic Cues of Deception in a Multilingual April Fools' Day Context","created":"2021-11-06","cited_by_count":1,"area":null},{"id":"2211.02415","title":"Multilingual Name Entity Recognition and Intent Classification Employing Deep Learning Architectures","created":"2022-11-04","cited_by_count":1,"area":null},{"id":"2309.07009","title":"OYXOY: A Modern NLP Test Suite for Modern Greek","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2407.09861","title":"A Systematic Survey of Natural Language Processing for the Greek Language","created":"2024-07-13","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":"2205.12012","title":"Analysing the Greek Parliament Records with Emotion Classification","created":"2022-05-24","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":"2407.09888","title":"FarFetched: Entity-centric Reasoning and Claim Validation for the Greek Language based on Textually Represented Environments","created":"2024-07-13","cited_by_count":0,"area":null},{"id":"2410.10290","title":"A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2410.12852","title":"The Large Language Model GreekLegalRoBERTa","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2412.08520","title":"GR-NLP-TOOLKIT: An Open-Source NLP Toolkit for Modern Greek","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2607.00970","title":"Svarna: An Open Corpus Workbench for Modern Greek","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2610.14101","title":"Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}