- Limitations and Challenges of Unsupervised Cross-lingual Pre-trainingPublication without faculty affiliation
- An Empirical Exploration of Local Ordering Pre-training for Structured PredictionPublication without faculty affiliation
- The Importance of Token Granularity Matching of Pre-trained Word Vectors for Deep Learning-Based Spam ClassificationPublication without faculty affiliation
- Grammatical Error Correction with Pre-trained Model and Multilingual Learner Corpus for Cross-lingual Transfer LearningPublication without faculty affiliation
- A BERT's Eye View: Identification of Irish Multiword Expressions Using Pre-trained Language ModelsPublication without faculty affiliation
- An Empirical Study of Pre-trained Transformers for Arabic Information ExtractionPublication without faculty affiliation
- MERGEDISTILL: Merging Pre-trained Language Models Using DistillationPublication without faculty affiliation
- Multilingual Probing of Deep Pre-Trained Contextual EncodersPublication without faculty affiliation
- Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained ModelsPublication without faculty affiliation
- Variable Mini-Batch Sizing and Pre-Trained Embeddings2017 | Faculty of Mathematics and Physics
- How Linguistically Fair Are Multilingual Pre-Trained Language Models?Publication without faculty affiliation
- XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and GenerationPublication without faculty affiliation
- AuGPT: Dialogue with Pre-trained Language Models and Data Augmentation2021 | Faculty of Mathematics and Physics
- BertOdia: BERT Pre-training for Low Resource Odia LanguagePublication without faculty affiliation
- On the Language Neutrality of Pre-trained Multilingual Representations2020 | Faculty of Mathematics and Physics
- Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-TrainingPublication without faculty affiliation
- Evaluating Pre-training Objectives for Low-Resource Translation into Morphologically Rich LanguagesPublication without faculty affiliation
- IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLPPublication without faculty affiliation
- AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models2021 | Faculty of Mathematics and Physics
- Benchmarking pre-trained language models for multilingual NER: TraSpaS at the BSNLP2021 shared taskPublication without faculty affiliation
- Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence RepresentationsPublication without faculty affiliation
- MLASK: Multimodal Summarization of Video-based News Articles2023 | Faculty of Mathematics and Physics
- Combining Static and Contextualised Multilingual Embeddings2022 | Faculty of Mathematics and Physics
- Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language ModelsPublication without faculty affiliation
- MLASK: Multimodal Summarization of Video-based News ArticlesPublication without faculty affiliation
- Introducing various semantic models for amharic: Experimentation and evaluation with multiple tasks and datasetsPublication without faculty affiliation
- Fact Search and Analysis ToolPublication without faculty affiliation
- Acoustic Emission and Feature Selection based on Sensitivity Analysis2001 | Faculty of Mathematics and Physics
- A Dataset and Strong Baselines for Classification of Czech News Texts2023 | Faculty of Mathematics and Physics
- ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT52021 | Faculty of Mathematics and Physics