Pheonix at SemEval-2020 Task 5: Masking the Labels Lubricates Models for Sequence Labeling

Pouria Babvey, Dario Borrelli, Yutong Zhao, Carlo Lipizzi


Abstract
This paper presents the deep-learning model that is submitted to the SemEval-2020 Task 5 competition: “Detecting Counterfactuals”. We participated in both Subtask1 and Subtask2. The model proposed in this paper ranked 2nd in Subtask2 “Detecting antecedent and consequence”. Our model approaches the task as a sequence labeling. The architecture is built on top of BERT, and a multi-head attention layer with label masking is used to benefit from the mutual information between nearby labels. Also, for prediction, a multi-stage algorithm is used in which the model finalize some predictions with higher certainty in each step and use them in the following. Our results show that masking the labels not only is an efficient regularization method but also improves the accuracy of the model compared with other alternatives like CRF. Label masking can be used as a regularization method in sequence labeling. Also, it improves the performance of the model by learning the specific patterns in the target variable.
Anthology ID:
2020.semeval-1.88
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Venues:
COLING | SemEval
SIGs:
SIGSEM | SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
677–682
Language:
URL:
https://aclanthology.org/2020.semeval-1.88
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.88.pdf