This repo provides the code for reproducing the experiments in Findings-EMNLP 2021 paper: RoR: Read-over-Read for Long Document Machine Reading Comprehension. This code is adapted from the repos of longformer.
Figure : Illustrations of RoR framework
transformers==2.11.0
torch>=1.6.0
pytorch-lightning==1.2.0
test-tube==0.7.5
We currently only open source the code in the TriviaQA dataset. To reproduce the results, you don’t have to train any model and can use the pretrained triviaqa-longformer-large to infer directly. The detailed inference steps are given in the inference.txt.
@inproceedings{zhao-etal-2021-ror-read,
title = "{R}o{R}: Read-over-Read for Long Document Machine Reading Comprehension",
author = "Zhao, Jing and
Bao, Junwei and
Wang, Yifan and
Zhou, Yongwei and
Wu, Youzheng and
He, Xiaodong and
Zhou, Bowen",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.160",
pages = "1862--1872",
}