{"total":44,"rows":[{"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":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36,"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":"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":"2108.13349","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","created":"2021-08-30","cited_by_count":22,"area":null},{"id":"2111.09453","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","created":"2021-11-18","cited_by_count":22,"area":null},{"id":"2203.03759","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","created":"2022-03-07","cited_by_count":20,"area":null},{"id":"2108.08688","title":"Contrastive Language-Image Pre-training for the Italian Language","created":"2021-08-19","cited_by_count":19,"area":null},{"id":"2109.12053","title":"Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus","created":"2021-09-24","cited_by_count":18,"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":"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":"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":"2210.00465","title":"Assessing the impact of contextual information in hate speech detection","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2106.09462","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2104.02061","title":"Query2Prod2Vec Grounded Word Embeddings for eCommerce","created":"2021-04-02","cited_by_count":8,"area":null},{"id":"2205.09744","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","created":"2022-05-19","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":"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":"2210.11359","title":"Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2211.11678","title":"Measuring Harmful Representations in Scandinavian Language Models","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2102.02111","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","created":"2021-02-03","cited_by_count":6,"area":null},{"id":"2212.09056","title":"Beyond Digital \"Echo Chambers\": The Role of Viewpoint Diversity in Political Discussion","created":"2022-12-18","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":"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":"2404.15737","title":"No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement","created":"2024-04-24","cited_by_count":5,"area":null},{"id":"2106.03983","title":"Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference","created":"2021-06-07","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":"2109.13037","title":"Language Invariant Properties in Natural Language Processing","created":"2021-09-27","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":"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":"2208.13947","title":"A Spanish dataset for Targeted Sentiment Analysis of political headlines","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2505.12160","title":"Emotion Recognition for Low-Resource Turkish: Fine-Tuning BERTurk on TREMO and Testing on Xenophobic Political Discourse","created":"2025-05-17","cited_by_count":1,"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":"2109.02966","title":"FH-SWF SG at GermEval 2021: Using Transformer-Based Language Models to Identify Toxic, Engaging, & Fact-Claiming Comments","created":"2021-09-07","cited_by_count":0,"area":null},{"id":"2110.02042","title":"ur-iw-hnt at GermEval 2021: An Ensembling Strategy with Multiple BERT Models","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2305.14481","title":"FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2309.13561","title":"Cordyceps@LT-EDI: Patching Language-Specific Homophobia/Transphobia Classifiers with a Multilingual Understanding","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2405.12711","title":"A Masked Semi-Supervised Learning Approach for Otago Micro Labels Recognition","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2406.06553","title":"Ensemble Model With Bert,Roberta and Xlnet For Molecular property prediction","created":"2024-05-30","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":"2501.11851","title":"Challenges in Expanding Portuguese Resources: A View from Open Information Extraction","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2512.15003","title":"SeBERTis: A Framework for Producing Classifiers of Security-Related Issue Reports","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2602.13504","title":"From Perceptions To Evidence: Detecting AI-Generated Content In Turkish News Media With A Fine-Tuned Bert Classifier","created":"2026-02-13","cited_by_count":0,"area":null}],"next_cursor":null}