ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)
- Chenyang Huang
- Amine Trabelsi
- Osmar R. Zaiane, University of Alberta (Database)
In this paper, we describe our mUlti-task learNIng for cOmmonsense reasoNing (UNION) system submitted for Task C of the SemEval2020 Task 4, which is to generate a reason explaining why a given false statement is non-sensical. However, we found in the early experiments that simple adaptations such as fine-tuning GPT2 often yield dull and non-informative generations (e.g. simple negations). In order to generate more meaningful explanations, we propose UNION, a unified end-to-end framework, to utilize several existing commonsense datasets so that it allows a model to learn more dynamics under the scope of commonsense reasoning. In order to perform model selection efficiently, accurately and promptly, we also propose a couple of auxiliary automatic evaluation metrics so that we can extensively compare the models from different perspectives. Our submitted system not only results in a good performance in the proposed metrics but also outperforms its competitors with the highest achieved score of 2.10 for human evaluation while remaining a BLEU score of 15.7. Our code is made publicly available at GitHub.
Citation
C. Huang, A. Trabelsi, O. Zaiane. "ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)". International Workshop on Semantic Evaluation (SemEval), June 2020.Keywords: | |
Category: | In Workshop |
Web Links: | arxiv |
BibTeX
@misc{Huang+al:(SemEval)20, author = {Chenyang Huang and Amine Trabelsi and Osmar R. Zaiane}, title = {ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)}, booktitle = {International Workshop on Semantic Evaluation (SemEval)}, year = 2020, }Last Updated: September 15, 2020
Submitted by Sabina P