Large-scale pre-trained models like BERT, have obtained a great success in various Natural
Language Processing (NLP) tasks, while it is still a challenge to adapt them to the math …

We study the utility of incorporating entity type abstractions into pre-trained Transformers
and test these methods on four NLP tasks requiring different forms of logical reasoning:(1) …

Machine Learning and Natural Language Processing are playing an increasingly vital role
in many different areas, including cybersecurity in Information Technology and Operational …

Compositionality---the principle that the meaning of a complex expression is built from the
meanings of its parts---is considered a central property of human language. This dissertation …

Natural language understanding (NLU) of user utterances is an essential task in dialogue
systems. However, existing machine learning models suffer from low accuracy in …

Understanding the learning dynamics of deep neural networks is of significant interest to the
research community as it can provide insights into the black box nature of neural nets. In this …

Generally, surveys are considered one of the popular mechanisms to collect data regarding
a problem associated with any field. The researchers use the collected data to conduct …

Deep representation learning has shown its effectiveness in many tasks such as text
classification and image processing. Many researches have been done to directly improve …

Interpreting the learning dynamics of neural networks can provide useful insights into how
networks learn and the development of better training and design approaches. We present …

Natural language has a sequential surface form, although its underlying structure has been
argued to be hierarchical and tree-structured in nature, whereby smaller linguistic units like …