UoR at SemEval-2020 Task 4: Pre-trained Sentence Transformer Models for Commonsense Validation and Explanation

Thanet Markchom, Bhuvana Dhruva, Chandresh Pravin, Huizhi Liang


Abstract
SemEval Task 4 Commonsense Validation and Explanation Challenge is to validate whether a system can differentiate natural language statements that make sense from those that do not make sense. Two subtasks, A and B, are focused in this work, i.e., detecting against-common-sense statements and selecting explanations of why they are false from the given options. Intuitively, commonsense validation requires additional knowledge beyond the given statements. Therefore, we propose a system utilising pre-trained sentence transformer models based on BERT, RoBERTa and DistillBERT architectures to embed the statements before classification. According to the results, these embeddings can improve the performance of the typical MLP and LSTM classifiers as downstream models of both subtasks compared to regular tokenised statements. These embedded statements are shown to comprise additional information from external resources which help validate common sense in natural language.
Anthology ID:
2020.semeval-1.52
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:
430–436
Language:
URL:
https://aclanthology.org/2020.semeval-1.52
DOI:
10.18653/v1/2020.semeval-1.52
Bibkey:
Cite (ACL):
Thanet Markchom, Bhuvana Dhruva, Chandresh Pravin, and Huizhi Liang. 2020. UoR at SemEval-2020 Task 4: Pre-trained Sentence Transformer Models for Commonsense Validation and Explanation. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 430–436, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
UoR at SemEval-2020 Task 4: Pre-trained Sentence Transformer Models for Commonsense Validation and Explanation (Markchom et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.52.pdf