ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)
This work addresses the problem of generating informative explanations in commonsense reasoning for NLP applications, representing an incremental improvement over existing methods.
The paper tackled generating meaningful explanations for nonsensical statements in commonsense reasoning by proposing a multi-task learning framework (UNION) that leverages existing datasets, resulting in a human evaluation score of 2.10 and a BLEU score of 15.7, outperforming competitors.
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.