With the rise in mobile and voice search, answer passage retrieval acts as a critical component of an effective information retrieval system for open domain question answering. Currently, there are no comparable collections that address non-factoid question answering within larger documents while simultaneously providing enough examples sufficient to train a deep neural network. In this paper, we introduce a new Wikipedia based collection specific for non-factoid answer passage retrieval containing thousands of questions with annotated answers and show benchmark results on a variety of state of the art neural architectures and retrieval models. The experimental results demonstrate the unique challenges presented by answer passage retrieval within topically relevant documents for future research.
@article{arxiv.1805.03797,
title = {WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval},
author = {Daniel Cohen and Liu Yang and W. Bruce Croft},
journal= {arXiv preprint arXiv:1805.03797},
year = {2018}
}