Zobrazeno 1 - 10
of 126
pro vyhledávání: '"Birch, Alexandra"'
Multilingual large language models (LLMs) have greatly increased the ceiling of performance on non-English tasks. However the mechanisms behind multilingualism in these LLMs are poorly understood. Of particular interest is the degree to which interna
Externí odkaz:
http://arxiv.org/abs/2406.09265
Researchers and practitioners operating on a limited budget face the cost-performance trade-off dilemma. The challenging decision often centers on whether to use a large LLM with better performance or a smaller one with reduced costs. This has motiva
Externí odkaz:
http://arxiv.org/abs/2405.02134
Bridging the significant gap between large language model's English and non-English performance presents a great challenge. While some previous studies attempt to mitigate this gap with translated training data, the recently proposed question alignme
Externí odkaz:
http://arxiv.org/abs/2405.01345
Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performance in Multilingual Pre-trained Language Models. However, a trade-off o
Externí odkaz:
http://arxiv.org/abs/2404.15737
The rise of Modular Deep Learning showcases its potential in various Natural Language Processing applications. Parameter-efficient fine-tuning (PEFT) modularity has been shown to work for various use cases, from domain adaptation to multilingual setu
Externí odkaz:
http://arxiv.org/abs/2403.18804
We propose a pretraining method to use Self-Supervised Speech (SSS) model to creating more compact Speech-to-text Translation. In contrast to using the SSS model for initialization, our method is more suitable to memory constrained scenario such as o
Externí odkaz:
http://arxiv.org/abs/2402.19333
Code switching (CS) is a very common phenomenon in written and spoken communication but one that is handled poorly by many natural language processing applications. Looking to the application of building CS corpora, we explore CS language identificat
Externí odkaz:
http://arxiv.org/abs/2402.01505
Speech-to-Text Translation (S2TT) has typically been addressed with cascade systems, where speech recognition systems generate a transcription that is subsequently passed to a translation model. While there has been a growing interest in developing d
Externí odkaz:
http://arxiv.org/abs/2402.00632
Autor:
Moghe, Nikita, Fazla, Arnisa, Amrhein, Chantal, Kocmi, Tom, Steedman, Mark, Birch, Alexandra, Sennrich, Rico, Guillou, Liane
Recent machine translation (MT) metrics calibrate their effectiveness by correlating with human judgement but without any insights about their behaviour across different error types. Challenge sets are used to probe specific dimensions of metric beha
Externí odkaz:
http://arxiv.org/abs/2401.16313
Autor:
Falis, Matúš, Gema, Aryo Pradipta, Dong, Hang, Daines, Luke, Basetti, Siddharth, Holder, Michael, Penfold, Rose S, Birch, Alexandra, Alex, Beatrice
Objective: To investigate GPT-3.5 in generating and coding medical documents with ICD-10 codes for data augmentation on low-resources labels. Materials and Methods: Employing GPT-3.5 we generated and coded 9,606 discharge summaries based on lists of
Externí odkaz:
http://arxiv.org/abs/2401.13512