• Publications
  • Influence
The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
TLDR
We model streams of discrete events in continuous time, by constructing a neurally self-modulating multivariate point process in which the intensities of multiple event types evolve according to a novel continuous-time LSTM. Expand
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
TLDR
We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization, without using any specialized features, resources, or generation templates. Expand
Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
TLDR
We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Expand
Coherent Dialogue with Attention-Based Language Models
TLDR
We model coherent conversation continuation via RNN-based dialogue models equipped with a dynamic attention mechanism. Expand
Imputing Missing Events in Continuous-Time Event Streams
TLDR
We propose particle smoothing---a form of sequential importance sampling---to impute the missing events in an incomplete sequence. Expand
Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification
TLDR
Learning how to predict future events from patterns of past events is difficult when the set of possible event types is large. Expand
Accurate Vision-based Vehicle Localization using Satellite Imagery
TLDR
We propose a method for accurately localizing ground vehicles with the aid of satellite imagery. Expand
Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction
TLDR
We propose a training method, called Halo, which enforces the local region of each hidden state of a neural model to only generate target tokens with the same semantic structure tag, thus yielding better generalization in both high and low resource settings. Expand
Noise-Contrastive Estimation for Multivariate Point Processes
TLDR
We show how to instead apply a version of noise-contrastive estimation---a general parameter estimation method with a less expensive stochastic objective to training a multivariate point process model. Expand
On the Idiosyncrasies of the Mandarin Chinese Classifier System
TLDR
We examine how much the uncertainty in Mandarin Chinese classifiers can be reduced by knowing semantic information about the nouns that the classifiers modify, and find that it is not fully idiosyncratic. Expand
...
1
2
...