{"total":109,"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":"2106.15147","title":"SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption","created":"2021-06-29","cited_by_count":156,"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":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"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":"2101.03289","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","created":"2021-01-09","cited_by_count":68,"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":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","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":"2102.13468","title":"The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates","created":"2021-02-24","cited_by_count":32,"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":"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":"2104.05591","title":"DATE: Detecting Anomalies in Text via Self-Supervision of Transformers","created":"2021-04-12","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":"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":"2305.06721","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","created":"2023-05-11","cited_by_count":24,"area":null},{"id":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23,"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":"2104.09243","title":"BERTi\\'c -- The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian","created":"2021-04-19","cited_by_count":21,"area":null},{"id":"2101.05716","title":"SICKNL: A Dataset for Dutch Natural Language Inference","created":"2021-01-14","cited_by_count":20,"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":"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":"2310.20384","title":"Do large language models solve verbal analogies like children do?","created":"2023-10-31","cited_by_count":13,"area":null},{"id":"2105.02855","title":"Adapting Monolingual Models: Data can be Scarce when Language Similarity is High","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2107.12930","title":"gaBERT -- an Irish Language Model","created":"2021-07-27","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":"2406.00016","title":"Exploration of Attention Mechanism-Enhanced Deep Learning Models in the Mining of Medical Textual Data","created":"2024-05-23","cited_by_count":11,"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":"2202.12312","title":"Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies","created":"2022-02-24","cited_by_count":9,"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":"2108.10640","title":"Are the Multilingual Models Better? Improving Czech Sentiment with Transformers","created":"2021-08-24","cited_by_count":7,"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":"2204.09145","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2301.08731","title":"Can Peanuts Fall in Love with Distributional Semantics?","created":"2023-01-20","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":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2411.12986","title":"Training Bilingual LMs with Data Constraints in the Targeted Language","created":"2024-11-20","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":"2408.17308","title":"Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation","created":"2024-08-30","cited_by_count":5,"area":null},{"id":"2412.07633","title":"ChocoLlama: Lessons Learned From Teaching Llamas Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2103.12312","title":"TMR: Evaluating NER Recall on Tough Mentions","created":"2021-03-23","cited_by_count":4,"area":null},{"id":"2104.10516","title":"Improving BERT Pretraining with Syntactic Supervision","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2204.13511","title":"RobBERTje: a Distilled Dutch BERT Model","created":"2022-04-28","cited_by_count":4,"area":null},{"id":"2307.13776","title":"Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word Representations","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2403.08693","title":"Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages","created":"2024-03-13","cited_by_count":4,"area":null},{"id":"2404.05428","title":"Language Models on a Diet: Cost-Efficient Development of Encoders for Closely-Related Languages via Additional Pretraining","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2507.16442","title":"Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch","created":"2025-07-22","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":"2112.04329","title":"JABER and SABER: Junior and Senior Arabic BERt","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2203.01063","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2203.12235","title":"Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2211.13703","title":"Multitask Learning for Low Resource Spoken Language Understanding","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2402.04812","title":"Aspect-Based Sentiment Analysis for Open-Ended HR Survey Responses","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2203.07362","title":"CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection","created":"2022-03-14","cited_by_count":2,"area":null},{"id":"2204.10710","title":"Tweets2Stance: Users stance detection exploiting Zero-Shot Learning Algorithms on Tweets","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2204.13535","title":"Machine Learning for Violence Risk Assessment Using Dutch Clinical Notes","created":"2022-04-28","cited_by_count":2,"area":null},{"id":"2211.05015","title":"Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2211.08192","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2301.03319","title":"FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers","created":"2023-01-09","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":"2305.13302","title":"Language-Agnostic Bias Detection in Language Models with Bias Probing","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2305.14917","title":"Structural Ambiguity and its Disambiguation in Language Model Based Parsers: the Case of Dutch Clause Relativization","created":"2023-05-24","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":"2309.05311","title":"Analysing Cross-Lingual Transfer in Low-Resourced African Named Entity Recognition","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2407.10991","title":"Classification of Geological Borehole Descriptions Using a Domain Adapted Large Language Model","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2503.00071","title":"I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialogue","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2506.12966","title":"Assessing the Role of Data Quality in Training Bilingual Language Models","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2108.00719","title":"ConveRT for FAQ Answering","created":"2021-08-02","cited_by_count":1,"area":null},{"id":"2109.06035","title":"Traffic Event Detection as a Slot Filling Problem","created":"2021-09-13","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":"2202.03907","title":"Context-Aware Discrimination Detection in Job Vacancies using Computational Language Models","created":"2022-02-02","cited_by_count":1,"area":null},{"id":"2204.13976","title":"Making sense of violence risk predictions using clinical notes","created":"2022-04-29","cited_by_count":1,"area":null},{"id":"2207.06839","title":"Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model","created":"2022-07-14","cited_by_count":1,"area":null},{"id":"2211.05025","title":"Local Structure Matters Most in Most Languages","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2212.06543","title":"Improving Stance Detection by Leveraging Measurement Knowledge from Social Sciences: A Case Study of Dutch Political Tweets and Traditional Gender Role Division","created":"2022-12-13","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":"2402.01352","title":"Describing Images $\\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2407.00648","title":"LegalTurk Optimized BERT for Multi-Label Text Classification and NER","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2412.08473","title":"Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation","created":"2024-12-11","cited_by_count":1,"area":"alignment"},{"id":"2502.13548","title":"Detecting Linguistic Bias in Government Documents Using Large language Models","created":"2025-02-19","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":"2106.02287","title":"Dutch Named Entity Recognition and De-identification Methods for the Human Resource Domain","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2110.05896","title":"LaoPLM: Pre-trained Language Models for Lao","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2211.14320","title":"Bidirectional Representations for Low Resource Spoken Language Understanding","created":"2022-11-24","cited_by_count":0,"area":null},{"id":"2212.04185","title":"Beyond Discrete Genres: Mapping News Items onto a Multidimensional Framework of Genre Cues","created":"2022-12-08","cited_by_count":0,"area":null},{"id":"2303.09115","title":"Learning for Amalgamation: A Multi-Source Transfer Learning Framework For Sentiment Classification","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2310.11965","title":"Filling in the Gaps: Efficient Event Coreference Resolution using Graph Autoencoder Networks","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2407.13097","title":"AlcLaM: Arabic Dialectal Language Model","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2408.06930","title":"Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2408.08694","title":"Quantifying the Effectiveness of Student Organization Activities using Natural Language Processing","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2411.18021","title":"Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?","created":"2024-11-27","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":"2506.12502","title":"Towards Fairness Assessment of Dutch Hate Speech Detection","created":"2025-06-14","cited_by_count":0,"area":null}],"next_cursor":"100"}