Our lab is currently working on application of NLP techniques to education, such as automated content analysis of students’ summaries for their understanding of a text or curriculum; on NLP and knowledge exploration, such as analysis of whether a knowledge source is relevant to an input natural language question; and novel environments to collect textual dialog data. To address these and other questions directed at computational models of language use, we collaborate with faculty and students in many departments.

These are exciting times for natural language processing (NLP) for many reasons, including renewed interest in Artificial Intelligence, a wealth of varied textual, semantic, social and multimodal data sources available on the web and from IoT, and a significant impact from NLP on data science. I am excited to have started a new NLP lab in the Department of Computer Science and Engineering at Penn State University, where I arrived in July 2016. My research interests are in computational pragmatics (language use and context). This is a challenging area because the words we use, the things we aim to do with words, the syntactic structures we use to assemble words into sentences, the freedom to invent new words, are all important aspects of language that can change significantly from context to context.