I completed my PhD under Professor James F. Allen in the Computer Science department at the University of Rochester (URCS). Currently I am working as a NLP Research Engineer in the R&D of Nuance Communications.

My research interests are in Natural Language Understanding (NLU) and Natural Language Processing (NLP), with focus on Temporal Information Processing, Information Extraction, Dialog Assistant, Social Media Text Analysis, Medical NLP, Question Answering, and Multimodal Summarization.

I primarily worked on problems related to Temporal Information Processing that are fundamental for deep language understanding and key to many applications, such as question answering, information extraction, timeline visualization, and document summarization. These techniques can be applied in news, medical, history and other domains. I implemented a state-of-the-art system to automatically extract temporal information (by extracting events, temporal expressions and identifying temporal relations between them) from raw text. Next, I developed a metric for evaluation of temporal annotation, which has been adopted by the premier temporal annotation challenge task. Finally, I worked on a question-answering system that can answer temporal questions with temporal reasoning and can evaluate temporal information understanding capability.

I also collaborate with Prof. Jeffrey P. Bigham on making information accessible. We proposed Multimodal Summarization to automatically illustrate complex sentences as multimodal summaries by combining picture, simple sentence structure and summarized text.

I have done multiple research internships in various domains on Big Data problems. I worked on game prediction using social media at Yahoo! Research. We extracted around 150K prediction tweets from 1.8 billion tweets by matching the syntactic structure of predictions. We created a prediction retrieval exploratory search application with the high-precision extracted predictions and aggregated the predictions to predict the most likely outcome of upcoming games. A key benefit of our framework is that it does not rely on the domain dependent knowledge for prediction, rather uses crowd's predictions from the social media. As a result, we can consider crowd's analysis about the event and by aggregating the predictions, we can predict the outcome of other future events discussed in the social media. At Microsoft Medical Media Lab, I implemented a system that can learn different patterns from user's examples and extract the pattern instances from natural language texts in medical domain. It was employed in The Washington Hospital Center and the staff found it useful. At Bosch RTC I developed a syntactic and semantic grammar for a commercial in-car dialog system. It was very similar to the famous Siri, iPhone's dialog assistant. Additionally I also worked on large scale data mining projects.

Before coming here at Rochester, I had worked two years (2005-2007) as a full-time Research Programmer for Center for Research on Bangla Language Processing (CRBLP) at BRAC University (Bangladesh). Details about my previous work and publications are available online.

I did my undergraduate studies on Computer Science at BRAC University, Bangladesh (2001-2005). Before that I spent an amazing six years in Faujdarhat Cadet College, Bangladesh (1995-2001).

Currently at Nuance Communications, I am working in the NLU Core Architecture group of Mobility Division.

CV, Research and Teaching Statements

If you are interested, here are my: CV, Research Statement, and Teaching Statement.
full LinkedIn profile (with recommendations at the end) [LinkedIn].

Naushad UzZaman's Google Citation Naushad UzZaman's bibliography View Naushad UzZaman's profile on LinkedIn

Locations of visitors to this page