State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while …
Some variants of self-supervised denoising objectives for pre-training encoder-decoder language models have been reported to have a negligible impact on downstream …
The ability of large language models (LLMs) to" learn in context" based on the provided prompt has led to an explosive growth in their use, culminating in the proliferation of AI …
S Toshniwal - arXiv preprint arXiv:2208.14252, 2022 - arxiv.org
What would it take for a natural language model to understand a novel, such as The Lord of the Rings? Among other things, such a model must be able to:(a) identify and record new …
N Shivagunde, V Lialin, A Rumshisky - arXiv preprint arXiv:2303.16445, 2023 - arxiv.org
Language model probing is often used to test specific capabilities of models. However, conclusions from such studies may be limited when the probing benchmarks are small and …
B Sayah, A Nehar, H Cherroun… - Proceedings of the 6th …, 2023 - aclanthology.org
BERT, a groundbreaking large language model, has excelled in natural language processing tasks such as question answering. Motivated by a desire to understand BERT's …
A Barrón-Cedeno, B Spallaccia, M Sosto, II Session - amslaurea.unibo.it
This thesis explores the evolving landscape of Natural Language Processing (NLP) and its intersection with societal biases, focusing on the LGBTQIA+ community. With the rise of …