@inproceedings{zhang2021poolingformer,
author = {Zhang, Hang and Gong, Yeyun and Shen, Yelong and Li, Weisheng and Lv, Jiancheng and Duan, Nan and Chen, Wei},
title = {Poolingformer: Long Document Modeling with Pooling Attention},
booktitle = {2021 International Conference on Machine Learning},
year = {2021},
month = {July},
abstract = {In this paper, we introduce a two-level attention schema, Poolingformer, for long document modeling. Its first level uses a smaller sliding window pattern to aggregate information from neighbors. Its second level employs a larger window to increase receptive fields with pooling attention to reduce both computational cost and memory consumption. We first evaluate Poolingformer on two long sequence QA tasks: the monolingual NQ and the multilingual TyDi QA. Experimental results show that Poolingformer sits atop three official leaderboards measured by F1, outperforming previous state-of-the-art models by 1.9 points (79.8 vs. 77.9) on NQ long answer, 1.9 points (79.5 vs. 77.6) on TyDi QA passage answer, and 1.6 points (67.6 vs. 66.0) on TyDi QA minimal answer. We further evaluate Poolingformer on a long sequence summarization task. Experimental results on the arXiv benchmark continue to demonstrate its superior performance.},
url = {http://approjects.co.za/?big=en-us/research/publication/poolingformer-long-document-modeling-with-pooling-attention/},
}