Official implementation of "Explicit Interaction Model towards Text Classification".

AAAI required us to upload the slides for the oral chance. We upload here and you can see it to help you understanding our paper. :)

Dependency:

• python 3.5
• MXNet 1.2
• One Titan XP

Use the preprocess python file from region embedding (ICLR 2018).

Please see the slides for some tricks in baselines.

We want to thanks Mr. Li (Yongqi Li AKA ASS LEE) who prepare the zhihu dataset for us, really appreciate for what he did.

Cunxiao Du, Zhaozheng Chin*, Fuli Feng*, Lei Zhu, Tian Gan, Liqiang Nie. Explicit Interaction Model towards Text Classification. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI).

Copyright (C) 2019 Shandong University.

Licence GPU GPL v3 or later, see http://www.gnu.org/licenses/. Distributed WITHOUT ANY WARRANTY.

This program is licensed under the GNU General Public License 3.0 (https://www.gnu.org/licenses/gpl-3.0.html). Any derivative work obtained under this license must be licensed under the GNU General Public License as published by the Free Software Foundation, either Version 3 of the License, or (at your option) any later version, if this derivative work is distributed to a third party.

The copyright for the program is owned by Shandong University. For commercial projects that require the ability to distribute the code of this program as part of a program that cannot be distributed under the GNU General Public License, please contact [email protected] to purchase a commercial license.

Please directly send me an email instead of leave issue here (because sometimes I will ignore it), but if you want to share your question, you could paste the question and my answer in the issue.