This paper aims to provide a comprehensive critical overview on how entities and their
interactions in Complex Networked Systems (CNS) are modelled across disciplines as they …

We present posterior regularization, a probabilistic framework for structured, weakly
supervised learning. Our framework efficiently incorporates indirect supervision via …

Mining detailed opinions buried in the vast amount of review text data is an important, yet
quite challenging task with widespread applications in multiple domains. Latent Aspect …

We propose a novel way to incorporate expert knowledge into the training of deep neural
networks. Many approaches encode domain constraints directly into the network …

Many reinforcement learning (RL) tasks, especially in robotics, consist of multiple sub-tasks
that are strongly structured. Such task structures can be exploited by incorporating …

It is difficult to apply machine learning to new domains because often we lack labeled
problem instances. In this paper, we provide a solution to this problem that leverages …

In this paper, we present an overview of generalized expectation criteria (GE), a simple,
robust, scalable method for semi-supervised training using weakly-labeled data. GE fits …

A major part of natural language processing now depends on the use of text data to build
linguistic analyzers. We consider statistical, computational approaches to modeling linguistic …

Existing Bayesian models, especially nonparametric Bayesian methods, rely on specially
conceived priors to incorporate domain knowledge for discovering improved latent …

We present a novel algorithm for multilingual dependency parsing that uses annotations
from a diverse set of source languages to parse a new unannotated language. Our …