@inproceedings{f1c7c44933954db1a2db518de53d0df1,
title = "A Case Study on Learning a Unified Encoder of Relations",
abstract = "Typical relation extraction models are trained on a single corpus annotated with a pre-defined relation schema. An individual corpus is often small, and the models may often be biased or overfitted to the corpus. We hypothesize that we can learn a better representation by combining multiple relation datasets. We attempt to use a shared encoder to learn the unified feature representation and to augment it with regularization by adversarial training. The additional corpora feeding the encoder can help to learn a better feature representation layer even though the relation schemas are different. We use ACE05 and ERE datasets as our case study for experiments. The multi-task model obtains significant improvement on both datasets.",
author = "Lisheng Fu and Bonan Min and Nguyen, {Thien Huu} and Ralph Grishman",
note = "Funding Information: This work was supported by DARPA/I2O Contract No. W911NF-18-C-0003 under the World Modelers program. The views, opinions, and/or findings contained in this article are those of the author and should not be interpreted as representing the official views or policies, either expressed or implied, of the Department of Defense or the U.S. Government. This document does not contain technology or technical data controlled under either the U.S. International Traffic in Arms Regulations or the U.S. Export Administration Regulations. Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics.; 4th Workshop on Noisy User-Generated Text, W-NUT 2018 ; Conference date: 01-11-2018",
year = "2018",
language = "English (US)",
series = "4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "202--207",
booktitle = "4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Proceedings of the Workshop",
}