Natural Language Proof Checking in Introduction to Proof Classes -- First Experiences with Diproche

no code implementations • 8 Feb 2022 • Merlin Carl, Hinrich Lorenzen, Michael Schmitz

We present and analyze the employment of the Diproche system, a natural language proof checker, within a one-semester mathematics beginners lecture with 228 participants.

From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project

no code implementations • 4 Sep 2019 • Peter Clark, Oren Etzioni, Daniel Khashabi, Tushar Khot, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Niket Tandon, Sumithra Bhakthavatsalam, Dirk Groeneveld, Michal Guerquin, Michael Schmitz

This paper reports unprecedented success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90% on the exam's non-diagram, multiple choice (NDMC) questions.

Multiple-choice Question Answering

AllenNLP: A Deep Semantic Natural Language Processing Platform

1 code implementation • WS 2018 • Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Peters, Michael Schmitz, Luke Zettlemoyer

This paper describes AllenNLP, a platform for research on deep learning methods in natural language understanding.

Natural Language Understanding Reading Comprehension +1

Open Language Learning for Information Extraction

no code implementations • CONLL 2012 • Mausam, Michael Schmitz, Stephen Soderland, Robert Bart, Oren Etzioni

Open Information Extraction Sentence