The Multimodal Video Search by Examples (MVSE) project investigates usin...
Prompt-based classifiers are an attractive approach for zero-shot
classi...
Evaluating Natural Language Generation (NLG) outputs is crucial but labo...
Multiple-choice reading and listening comprehension tests are an importa...
Multiple Choice examinations are a ubiquitous form of assessment that is...
In this paper, we consider the challenge of summarizing patients' medica...
State-of-the-art sequence-to-sequence models often require autoregressiv...
Generative Large Language Models (LLMs) such as GPT-3 are capable of
gen...
The emergence of pretrained large language models has led to the deploym...
State-of-the-art summarization systems can generate highly fluent summar...
Recently it has been shown that without any access to the contextual pas...