Careful Selection of Knowledge to solve Open Book Question Answering
This addresses the problem of deeper reasoning in QA for researchers, though it is incremental as it builds on existing methods.
The paper tackled open book question answering by combining language models with abductive IR, re-ranking, and selection techniques, achieving 72.0% accuracy, an 11.6% improvement over the state of the art.
Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA tasks that focus on linguistic understanding, OpenBookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.