Data augmentation has recently seen increased interest in NLP due to more work in low-
resource domains, new tasks, and the popularity of large-scale neural networks that require …

Abstract Streaming Machine Translation (MT) is the task of translating an unbounded input
text stream in real-time. The traditional cascade approach, which combines an Automatic …

Simultaneous Machine Translation is the task of incrementally translating an input sentence
before it is fully available. Currently, simultaneous translation is carried out by translating …

A challenge in spoken language translation is that plenty of spoken content is long-form, but
short units are necessary for obtaining high-quality translations. To address this mismatch …

One challenge in speech translation is that plenty of spoken content is long-form, but short
units are necessary for obtaining high-quality translations. To address this mismatch, we …

Machine translation—the automatic transformation of one natural language (source
language) into another (target language) through computational means—occupies a central …

With the recent increase in low-resource African language text corpora, there have been
advancements which have led to development of multilingual pre-trained language models …

Abstract “Who said what” is essential for users to understand video streams that have more
than one speaker, but conventional simultaneous interpretation systems merely present …

In natural language processing, much current research focuses on training larger and larger
models on more and more data. In this thesis, we argue that how data is represented can …

Despite a narrowed performance gap with direct approaches, cascade solutions, involving
automatic speech recognition (ASR) and machine translation (MT) are still largely employed …