{"total":143,"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":"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":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"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":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"area":null},{"id":"2104.12741","title":"GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval","created":"2021-04-26","cited_by_count":39,"area":null},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"area":null},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"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":"2212.10503","title":"Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2201.02495","title":"Sign Language Video Retrieval with Free-Form Textual Queries","created":"2022-01-07","cited_by_count":23,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2107.10314","title":"Small-Text: Active Learning for Text Classification in Python","created":"2021-07-21","cited_by_count":19,"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":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","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":"2203.09904","title":"Do Multilingual Language Models Capture Differing Moral Norms?","created":"2022-03-18","cited_by_count":15,"area":null},{"id":"2210.06312","title":"Changing the Representation: Examining Language Representation for Neural Sign Language Production","created":"2022-09-16","cited_by_count":15,"area":null},{"id":"2110.06874","title":"Automated Essay Scoring Using Transformer Models","created":"2021-10-13","cited_by_count":14,"area":null},{"id":"2305.12092","title":"ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain","created":"2023-05-20","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":"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":"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":"2401.02709","title":"German Text Embedding Clustering Benchmark","created":"2024-01-05","cited_by_count":13,"area":null},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","cited_by_count":13,"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":"2310.03477","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2303.08179","title":"MEDBERT.de: A Comprehensive German BERT Model for the Medical Domain","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2303.13310","title":"SwissBERT: The Multilingual Language Model for Switzerland","created":"2023-03-23","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":"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":"2403.12749","title":"Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2109.03094","title":"FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning","created":"2021-09-07","cited_by_count":7,"area":null},{"id":"2209.04299","title":"Automatic Readability Assessment of German Sentences with Transformer Ensembles","created":"2022-09-09","cited_by_count":7,"area":null},{"id":"2303.10227","title":"Conversational Tree Search: A New Hybrid Dialog Task","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2403.10293","title":"MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank","created":"2024-03-15","cited_by_count":7,"area":null},{"id":"2412.09415","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2109.06605","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2109.07346","title":"Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community","created":"2021-09-15","cited_by_count":6,"area":null},{"id":"2209.10335","title":"Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling","created":"2022-09-21","cited_by_count":6,"area":null},{"id":"2212.10522","title":"Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2303.05388","title":"German BERT Model for Legal Named Entity Recognition","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","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":"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":"2109.01942","title":"On the ability of monolingual models to learn language-agnostic representations","created":"2021-09-04","cited_by_count":5,"area":null},{"id":"2205.10233","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","created":"2022-04-27","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":"2308.13170","title":"Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese","created":"2023-08-25","cited_by_count":5,"area":null},{"id":"2310.07321","title":"On the Impact of Cross-Domain Data on German Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2404.02761","title":"AQuA -- Combining Experts' and Non-Experts' Views To Assess Deliberation Quality in Online Discussions Using LLMs","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2409.17929","title":"The Lou Dataset -- Exploring the Impact of Gender-Fair Language in German Text Classification","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2503.02056","title":"CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2505.13136","title":"New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models","created":"2025-05-19","cited_by_count":5,"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":"2309.14355","title":"PopBERT. Detecting populism and its host ideologies in the German Bundestag","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2406.06809","title":"AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2406.08080","title":"AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2506.11903","title":"GeistBERT: Breathing Life into German NLP","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2509.05668","title":"Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian","created":"2025-09-06","cited_by_count":4,"area":null},{"id":"2510.21364","title":"SindBERT, the Sailor: Charting the Seas of Turkish NLP","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2108.00057","title":"WLV-RIT at GermEval 2021: Multitask Learning with Transformers to Detect Toxic, Engaging, and Fact-Claiming Comments","created":"2021-07-30","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":"2205.10023","title":"Transition-based Semantic Role Labeling with Pointer Networks","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2212.09682","title":"Multilingual Sequence-to-Sequence Models for Hebrew NLP","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2308.04248","title":"Gloss Alignment Using Word Embeddings","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2310.04632","title":"Automatic Anonymization of Swiss Federal Supreme Court Rulings","created":"2023-10-07","cited_by_count":3,"area":null},{"id":"2403.17143","title":"Guided Distant Supervision for Multilingual Relation Extraction Data: Adapting to a New Language","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.11532","title":"Select and Reorder: A Novel Approach for Neural Sign Language Production","created":"2024-04-17","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":"2501.01256","title":"Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2501.03863","title":"Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study","created":"2025-01-07","cited_by_count":3,"area":null},{"id":"2504.19856","title":"Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2205.10687","title":"Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding","created":"2022-05-21","cited_by_count":2,"area":null},{"id":"2207.06265","title":"A Transfer Learning Based Model for Text Readability Assessment in German","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2208.07846","title":"TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation","created":"2022-08-16","cited_by_count":2,"area":null},{"id":"2212.05764","title":"Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2304.09957","title":"Low-resource Bilingual Dialect Lexicon Induction with Large Language Models","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2308.04645","title":"Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach","created":"2023-08-09","cited_by_count":2,"area":null},{"id":"2402.06584","title":"G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2403.13369","title":"Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2404.06621","title":"What is Your Favorite Gender, MLM? Gender Bias Evaluation in Multilingual Masked Language Models","created":"2024-04-09","cited_by_count":2,"area":null},{"id":"2406.18239","title":"Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2407.14878","title":"Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2409.02690","title":"Detecting Calls to Action in Multimodal Content: Analysis of the 2021 German Federal Election Campaign on Instagram","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2505.10945","title":"Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.15682","title":"The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effect","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.17950","title":"Evaluating NLP Embedding Models for Handling Science-Specific Symbolic Expressions in Student Texts","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2105.05557","title":"Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2202.02268","title":"StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements?","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2202.05778","title":"White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense","created":"2022-02-11","cited_by_count":1,"area":null},{"id":"2206.12664","title":"Evaluation of Semantic Answer Similarity Metrics","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2208.09243","title":"Pseudo-Labels Are All You Need","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2209.11035","title":"MonoByte: A Pool of Monolingual Byte-level Language Models","created":"2022-09-22","cited_by_count":1,"area":null}],"next_cursor":"100"}