ANA at SemEval-2020 Task 4: MUlti-task learNIng for cOmmonsense reasoNing (UNION)

Anandh Konar, Chenyang Huang, Amine Trabelsi, Osmar Zaiane


Abstract
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.
Anthology ID:
2020.semeval-1.45
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Editors:
Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
Venue:
SemEval
SIG:
SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
367–373
Language:
URL:
https://aclanthology.org/2020.semeval-1.45
DOI:
10.18653/v1/2020.semeval-1.45
Bibkey:
Cite (ACL):
Anandh Konar, Chenyang Huang, Amine Trabelsi, and Osmar Zaiane. 2020. ANA at SemEval-2020 Task 4: MUlti-task learNIng for cOmmonsense reasoNing (UNION). In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 367–373, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
ANA at SemEval-2020 Task 4: MUlti-task learNIng for cOmmonsense reasoNing (UNION) (Konar et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.45.pdf
Code
 anandhperumal/ANA-at-SemEval-2020-Task-4-UNION
Data
CoS-E