Search Results - "Bojar, Ondřej"

Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals by Popel, Martin, Tomkova, Marketa, Tomek, Jakub, Kaiser, Łukasz, Uszkoreit, Jakob, Bojar, Ondřej, Žabokrtský, Zdeněk

“…The quality of human translation was long thought to be unattainable for computer translation systems. In this study, we present a deep-learning system,…”
Get full text

Keyphrase Generation: A Multi-Aspect Survey by Cano, Erion, Bojar, Ondrej

“…Extractive keyphrase generation research has been around since the nineties, but the more advanced abstractive approach based on the encoder-decoder framework…”
Get full text

Understanding the role of FFNs in driving multilingual behaviour in LLMs by Bhattacharya, Sunit, Bojar, Ondřej

“…Multilingualism in Large Language Models (LLMs) is an yet under-explored area. In this paper, we conduct an in-depth analysis of the multilingual capabilities…”
Get full text

Quality and Quantity of Machine Translation References for Automatic Metrics by Zouhar, Vilém, Bojar, Ondřej

“…Automatic machine translation metrics typically rely on human translations to determine the quality of system translations. Common wisdom in the field dictates…”
Get full text

Boosting Unsupervised Machine Translation with Pseudo-Parallel Data by Kvapilíková, Ivana, Bojar, Ondřej

“…Ivana Kvapil\'ikov\'a, Ond\v{r}ej Bojar (2023): Boosting Unsupervised Machine Translation with Pseudo-Parallel Data. In: Proceedings of Machine Translation…”
Get full text

Long-Form End-to-End Speech Translation via Latent Alignment Segmentation by Polák, Peter, Bojar, Ondřej

“…Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into…”
Get full text

Minuteman: Machine and Human Joining Forces in Meeting Summarization by Kmječ, František, Bojar, Ondřej

“…Many meetings require creating a meeting summary to keep everyone up to date. Creating minutes of sufficient quality is however very cognitively demanding…”
Get full text

Character-level NMT and language similarity by Jon, Josef, Bojar, Ondřej

“…We explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of…”
Get full text

Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation by Jon, Josef, Bojar, Ondřej

“…We propose a genetic algorithm (GA) based method for modifying n-best lists produced by a machine translation (MT) system. Our method offers an innovative…”
Get full text

Sequence Length is a Domain: Length-based Overfitting in Transformer Models by Variš, Dušan, Bojar, Ondřej

“…Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from…”
Get full text

Coarse-To-Fine And Cross-Lingual ASR Transfer by Polák, Peter, Bojar, Ondřej

“…End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing…”
Get full text

Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers by Zavoral, Patrik, Variš, Dušan, Bojar, Ondřej

“…The Transformer model has a tendency to overfit various aspects of the training data, such as the overall sequence length. We study elementary string edit…”
Get full text

Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation by Variš, Dušan, Bojar, Ondřej

“…This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the…”
Get full text

Presenting Simultaneous Translation in Limited Space by Macháček, Dominik, Bojar, Ondřej

“…ITAT WAFNL 2020 Some methods of automatic simultaneous translation of a long-form speech allow revisions of outputs, trading accuracy for low latency…”
Get full text

Automating Text Naturalness Evaluation of NLG Systems by Çano, Erion, Bojar, Ondřej

“…Automatic methods and metrics that assess various quality criteria of automatically generated texts are important for developing NLG systems because they…”
Get full text

Turning Whisper into Real-Time Transcription System by Macháček, Dominik, Dabre, Raj, Bojar, Ondřej

“…Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription…”
Get full text

Human or Machine: Automating Human Likeliness Evaluation of NLG Texts by Çano, Erion, Bojar, Ondřej

“…Automatic evaluation of various text quality criteria produced by data-driven intelligent methods is very common and useful because it is cheap, fast, and…”
Get full text

Assessing Word Importance Using Models Trained for Semantic Tasks by Javorský, Dávid, Bojar, Ondřej, Yvon, François

“…Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve…”
Get full text

Two Huge Title and Keyword Generation Corpora of Research Articles by Çano, Erion, Bojar, Ondřej

“…Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and…”
Get full text

Multimodal Shannon Game with Images by Zouhar, Vilém, Bhattacharya, Sunit, Bojar, Ondřej

“…The Shannon game has long been used as a thought experiment in linguistics and NLP, asking participants to guess the next letter in a sentence based on its…”
Get full text