Peter Jansen

Multi-class Hierarchical Question Classification for Multiple Choice Science Exams

2019 · arXiv (Cornell University)

Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity …

TextGraphs 2019 Shared Task on Multi-Hop Inference for Explanation Regeneration

2019

While automated question answering systems are increasingly able to retrieve answers to natural language questions, their ability to generate detailed human-readable explanations for their answers is still quite limited. The Shared Task on Multi-Hop Inference …

QASC: A Dataset for Question Answering via Sentence Composition

2020

Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus …

WorldTree V2: A corpus of science-domain structured explanations and inference patterns supporting multi-hop inference

2020 · UA Campus Repository (The University of Arizona)

Explainable question answering for complex questions often requires combining large numbers of facts to answer a question while providing a human-readable explanation for the answer, a process known as multi-hop inference. Standardized science questions require …