Bhavana Dalvi Mishra

TL;DR: WIQA, the first large-scale dataset of “What if...” questions over procedural text, is introduced and it is found that state-of-the-art models achieve 73.8% accuracy, well below the human performance of 96.3%.

TL;DR: This work has created a domain-targeted, high precision knowledge extraction pipeline, leveraging Open IE, crowdsourcing, and a novel canonical schema learning algorithm (called CASI), that produces high precisionknowledge targeted to a particular domain - in this case, elementary science.

TL;DR: For example, the authors reported success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90 percent on the exam's NDMC (non-diagram, multiple choice) questions.

TL;DR: This paper shows how the predicted effects of actions in the context of a paragraph can be improved in two ways: by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and by biasing reading with preferences from large-scale corpora.

TL;DR: Success is reported on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90 percent on the exam’s nondiagram, multiple choice (NDMC) questions, demonstrating that modern natural language processing methods can result in mastery on this task.