HFL at SemEval-2022 Task 8: A Linguistics-inspired Regression Model with Data Augmentation for Multilingual News Similarity
Zihang Xu, Ziqing Yang, Yiming Cui, Zhigang Chen · Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022) · 2022
This paper describes our system designed for SemEval-2022 Task 8: Multilingual News Article Similarity.We proposed a linguisticsinspired model trained with a few task-specific strategies.The main techniques of our system are: 1) data augmentation, 2) multi-label loss, 3) adapted R-Drop, 4) samples reconstruction with the head-tail combination.We also present a brief analysis of some negative methods like two-tower architecture.Our system ranked 1st on the leaderboard while achieving a Pearson's Correlation Coefficient of 0.818 on the official evaluation set.