Natural Language Premise Selection: Finding Supporting Statements for Mathematical Text
This addresses the problem of understanding and reasoning with mathematical text for NLP researchers, though it is incremental as it focuses on a specific new task and dataset.
The authors introduced a new NLP task called natural premise selection to retrieve supporting definitions and propositions for generating informal mathematical proofs, and they released a dataset named NL-PS to evaluate approaches, demonstrating interpretation challenges with baselines.
Mathematical text is written using a combination of words and mathematical expressions. This combination, along with a specific way of structuring sentences makes it challenging for state-of-art NLP tools to understand and reason on top of mathematical discourse. In this work, we propose a new NLP task, the natural premise selection, which is used to retrieve supporting definitions and supporting propositions that are useful for generating an informal mathematical proof for a particular statement. We also make available a dataset, NL-PS, which can be used to evaluate different approaches for the natural premise selection task. Using different baselines, we demonstrate the underlying interpretation challenges associated with the task.