The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …

We investigate what kind of structural knowledge learned in neural network encoders is
transferable to processing natural language. We design artificial languages with structural …

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-
crafted feature-based models, we struggle to comprehend the concepts learned and how …

Recurrent Neural Networks (RNNs) are theoretically Turing-complete and established
themselves as a dominant model for language processing. Yet, there still remains an …

Recent work in NLP shows that LSTM language models capture hierarchical structure in
language data. In contrast to existing work, we consider the\textit {learning} process that …

The ability for variation in language use is necessary for speakers to achieve their
conversational goals, for instance when referring to objects in visual environments. We …

We show that the state of the art Transformer Machine Translation (MT) model is not biased
towards monotonic reordering (unlike previous recurrent neural network models), but that …

One proposal that can explain the remarkable pace of word learning in young children is
that they leverage the language-internal distributional similarity of familiar and novel words …

A glut of recent research shows that language models capture linguistic structure. Linzen et
al.(2016) found that LSTM-based language models may encode syntactic information …

Long Short-Term Memory recurrent neural network (LSTM) is widely used and known to
capture informative long-term syntactic dependencies. However, how such information are …