XSYSIGMA at SemEval-2020 Task 7: Method for Predicting Headlines’ Humor Based on Auxiliary Sentences with EI-BERT

Jian Ma, ShuYi Xie, Meizhi Jin, Jiang Lianxin, Mo Yang, Jianping Shen


Abstract
This paper describes xsysigma team’s system for SemEval 2020 Task 7: Assessing the Funniness of Edited News Headlines. The target of this task is to assess the funniness changes of news headlines after minor editing and is divided into two subtasks: Subtask 1 is a regression task to detect the humor intensity of the sentence after editing; and Subtask 2 is a classification task to predict funnier of the two edited versions of an original headline. In this paper, we only report our implement of Subtask 2. We first construct sentence pairs with different features for Enhancement Inference BERT(EI-BERT)’s input. We then conduct data augmentation strategy and Pseudo-Label method. After that, we apply feature enhancement interaction on the encoding of each sentence for classification with EI-BERT. Finally, we apply weighted fusion algorithm to the logits results which obtained by different pre-trained models. We achieve 64.5% accuracy in subtask2 and rank the first and the fifth in dev and test dataset 1 , respectively.
Anthology ID:
2020.semeval-1.142
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:
1077–1084
Language:
URL:
https://aclanthology.org/2020.semeval-1.142
DOI:
10.18653/v1/2020.semeval-1.142
Bibkey:
Cite (ACL):
Jian Ma, ShuYi Xie, Meizhi Jin, Jiang Lianxin, Mo Yang, and Jianping Shen. 2020. XSYSIGMA at SemEval-2020 Task 7: Method for Predicting Headlines’ Humor Based on Auxiliary Sentences with EI-BERT. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1077–1084, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
XSYSIGMA at SemEval-2020 Task 7: Method for Predicting Headlines’ Humor Based on Auxiliary Sentences with EI-BERT (Ma et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.142.pdf