Retrieving information from correlative paragraphs or documents to answer open-domain multi-hop questions is very challenging. To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose graph-based methods to retrieve them. However, in this paper, we point out the intrinsic defect of such methods. Instead, we propose a new architecture that models paragraphs as sequential data and considers multi-hop information retrieval as a kind of sequence labeling task. Specifically, we design a rewritable external memory to model the dependency among paragraphs. Moreover, a threshold gate mechanism is proposed to eliminate the distraction of noise paragraphs. We evaluate our method on both full wiki and distractor subtask of HotpotQA, a public textual multi-hop QA dataset requiring multi-hop information retrieval. Experiments show that our method achieves significant improvement over the published state-of-the-art method in retrieval and downstream QA task performance.
@article{arxiv.2102.03741,
title = {Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering},
author = {Nan Shao and Yiming Cui and Ting Liu and Shijin Wang and Guoping Hu},
journal= {arXiv preprint arXiv:2102.03741},
year = {2021}
}