Automatically generating the “impression” section of a radiology report given the “findings”
section can summarize as much salient information of the “findings” section as possible, thus …

For many new application domains for data-to-text generation, the main obstacle in training
neural models consists of a lack of training data. While usually large numbers of instances …

Large-scale pretrained language models have led to dramatic improvements in text
generation. Impressive performance can be achieved by finetuning only on a small number …

Recent advancements in data-to-text generation largely take on the form of neural end-to-
end systems. Efforts have been dedicated to improving text generation systems by changing …

Objective Weak supervision holds significant promise to improve clinical natural language
processing by leveraging domain resources and expertise instead of large manually …

This paper explores deep latent variable models for semi-supervised paraphrase
generation, where the missing target pair for unlabelled data is modelled as a latent …

\AcpMDS aim to assist doctors and patients with a range of professional medical services, ie,
diagnosis, treatment and consultation. The development of\acpMDS is hindered because of …

This study discusses the effect of semi-supervised learning in combination with pretrained
language models for data-to-text generation. It is not known whether semi-supervised …

West African Pidgin English is a language that is significantly spoken in West Africa,
consisting of at least 75 million speakers. Nevertheless, proper machine translation systems …

Incorporating conversational context and knowledge into dialogue generation models has
been essential for improving the quality of the generated responses. The context, comprising …