Subword segmenters like BPE operate as a preprocessing step in neural ma...
The paper describes the University of Cape Town's submission to the
cons...
Subwords have become the standard units of text in NLP, enabling efficie...
Language models are the foundation of current neural network-based model...
Morphological Segmentation involves decomposing words into morphemes, th...
The principle of the Information Bottleneck (Tishby et al. 1999) is to
p...
We propose neural models to generate high-quality text from structured
r...
Despite considerable advancements with deep neural language models, the
...
Recurrent Neural Networks (RNNs) are powerful autoregressive sequence mo...
Parsing sentences to linguistically-expressive semantic representations ...
We introduce an online neural sequence to sequence model that learns to
...
Morphologically rich languages often lack the annotated linguistic resou...