careers

Automatic summarization of related documents

The intern will work with a team of human-information interaction researchers to create software that automatically generates textual and visualization summaries of a topic, given information gathered from many documents on that topic. We will use linguistic analysis of the documents to build a knowledge representation and reason over it to produce the summaries.

Responsibilities

This project will involve integrating computational linguistics, knowledge representation, user interface, and visualization technologies to produce a new kind of summary of a topic. Possible examples include:

• systems that read through reports of medical trials to summarize the state-of-the-art in treating a particular disease;
• systems that read through articles about a particular person and summarize their career or their travels.

Requirements:

• Bachelor's degree in computer science or a related field
  
• Experience with Java and/or Python
• User interface design
• Some familiarity with computational linguistics
  
• Knowledge representations would also be helpful