Modeling asynchronous event sequences with RNNs

Discrete Event, Continuous Time RNNs

We investigate recurrent neural network architectures for event-sequence processing. Event sequences, characterized by discrete observations stamped with continuous-valued times of occurrence, are challenging due to the potentially wide dynamic range of relevant time scales as well as interactions between time scales. We describe four forms of inductive bias that should benefit architectures fo...

Actionable Email Intent Modeling with Reparametrized RNNs

Emails in the workplace are often intentional calls to action for its recipients. We propose to annotate these emails for what action its recipient will take. We argue that our approach of action-based annotation is more scalable and theoryagnostic than traditional speech-act-based email intent annotation, while still carrying important semantic and pragmatic information. We show that our actio...

Modeling, Learning, and Inference of High-Dimensional Asynchronous Event Data

Modeling Missing Data in Clinical Time Series with RNNs

We demonstrate a simple strategy to cope with missing data in sequential inputs, addressing the task of multilabel classification of diagnoses given clinical time series. Collected from the intensive care unit (ICU) of a major urban medical center, our data consists of multivariate time series of observations. The data is irregularly sampled, leading to missingness patterns in re-sampled sequen...

Self-exciting point process modeling of conversation event sequences

Self-exciting processes of Hawkes type have been used to model various phenomena including earthquakes, neural activities, and views of online videos. Studies of temporal networks have revealed that sequences of social interevent times for individuals are highly bursty. We examine some basic properties of event sequences generated by the Hawkes self-exciting process to show that it generates bu...