If we take an existing supervised NLP system, a simple and general way to improve
accuracy is to use unsupervised word representations as extra word features. We evaluate …

Finding the right representations for words is critical for building accurate NLP systems when
domain-specific labeled data for the task is scarce. This article investigates novel techniques …

Finding the right representation for words is critical for building accurate NLP systems when
domain-specific labeled data for the task is scarce. This paper investigates language model …

We present a method that learns bilexical operators over distributional representations of
words and leverages supervised data for a linguistic relation. The learning algorithm exploits …

Most representation learning algorithms for language and image processing are local, in
that they identify features for a data point based on surrounding points. Yet in language …

A metonym is a word with a figurative meaning, similar to a metaphor. Because metonyms
are closely related to metaphors, we apply features that are used successfully for metaphor …

The Chinese language poses challenges for natural language processing based on the unit
of a word even for formal uses of the Chinese language, social media only makes word …

In recent decades, the society depends more and more on computers for a large number of
tasks. The first steps in NLP applications involve identification of topics, entities, concepts …

News media play a key role in shaping the public understanding of scientific issues.
Different news media frame stories in various ways to promote a particular viewpoint, and …

Good representations are crucial for the development of high-quality artificially intelligent
systems. This dissertation addresses the problem of how to apply machine learning to build …