Semantic parsing is an important NLP problem, particularly for voice assistants such as
Alexa and Google Assistant. State-of-the-art (SOTA) semantic parsers are seq2seq …

Learning how to predict future events from patterns of past events is difficult when the set of
possible event types is large. Training an unrestricted neural model might overfit to spurious …

The historical motivation for serverless comes from internet-of-things, smartphone client
server, and the objective of simplifying programming (no provisioning) and scale-down (pay …

Voice assistants such as Amazon Alexa, Apple Siri, and Google Assistant have become
ubiquitous. They rely on spoken language understanding, which typically consists of an …

This thesis focuses on modeling event sequences, namely, sequences of discrete events in
continuous time. We build a family of generative probabilistic models that is able to reason …