Yseop at SemEval-2020 Task 5: Cascaded BERT Language Model for Counterfactual Statement Analysis
This work addresses the challenge of modeling causal reasoning in language for tasks like counterfactual analysis, but it is incremental as it builds on existing BERT models with hybrid features.
The paper tackled the problem of detecting and evaluating counterfactual sentences in natural language processing, achieving F1 scores of 85.00% in Task 1 and 83.90% in Task 2 by using a cascaded BERT-based system that outperformed methods like BiLSTM-CRF.
In this paper, we explore strategies to detect and evaluate counterfactual sentences. We describe our system for SemEval-2020 Task 5: Modeling Causal Reasoning in Language: Detecting Counterfactuals. We use a BERT base model for the classification task and build a hybrid BERT Multi-Layer Perceptron system to handle the sequence identification task. Our experiments show that while introducing syntactic and semantic features does little in improving the system in the classification task, using these types of features as cascaded linear inputs to fine-tune the sequence-delimiting ability of the model ensures it outperforms other similar-purpose complex systems like BiLSTM-CRF in the second task. Our system achieves an F1 score of 85.00% in Task 1 and 83.90% in Task 2.