textgraphs2018_jansen_slides

AI2 Talk: What’s in an Explanation? Toward Explanation-centered Inference for Science Exams

I recently gave a talk at the Allen Institute for Artificial Intelligence (AI2) on my work in explanation-centered inference for solving standardized science exams. This talk is a good high-level introduction to three recent papers on understanding the kinds of knowledge and inference required to build explanations (COLING 2016), our work in building a very large corpus of semi-structured explanations (the largest I’m aware of) to help us learn how to combine large amounts of information for inference (LREC 2018), and examining this corpus for common explanatory patterns that would help us make the task of building new explanations easier (AKBC 2017).

We’re very excited about this new knowledge resource that’s been two years in the making, and it’s potential for exploring explanation-centered inference. The Worldtree corpus is available here, at the Explanation Bank!

textgraphs2018_jansen_slides

Looking for Postdoctoral Fellow

I am looking for a postdoctoral researcher in natural language processing to work on several projects in question answering, automated inference, and information extraction centered around constructing human-readable explanations supporting inferences, as well as various applied projects.

More details:

  • You should have a PhD in computer science, cognitive science, computational linguistics, or a closely related field.
  • As an empirical lab, we need someone who likes to build and experiment with moderately complex, large-scale, multi-investigator systems.
  • Interest in working in a highly collaborative interdisciplinary team

Preferred Qualifications:

  • The ideal candidate will know about modern natural language processing and machine learning techniques, though this isn’t necessary if the candidate has expertise in other relevant areas.
  • Prior experience or interest in writing grant proposals
  • Interest in knowledge representation, inference, and/or visualization.

Please get in touch (pajansen@email.arizona.edu) if you would like to learn more. The start date is flexible.