Natural Language Processing Intern

Built a machine reading system; capabilities included answering questions requiring complex reasoning and understanding of the relation between entities/events in paragraphs involving biological processes. Demonstrated question answering with a rich structure representing the bioprocess predicted improved accuracy. Awarded best paper at 2014 Empirical Methods in NLP “Modeling Biological Processes for Reading Comprehension”. Abstract: Machine reading calls for programs that read and understand text, but most current work only attempts to extract facts from redundant web-scale corpora. We focus on a new reading comprehension task that requires complex reasoning over a single document. The input is a paragraph describing a biological process, and the goal is to answer questions that require an understanding of the relations between entities and events in the process. To answer the questions, we first predict a rich structure representing the process in the paragraph. Then, we map the question to a formal query, which is executed against the predicted structure. We demonstrate that answering questions via predicted structures substantially improves accuracy over baselines that use shallower representations. Natural Language Processing (NLP), Knowledge Graph-Based Question Answering and +3 skills