BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models
This work addresses a specific NLP task for researchers, but it is incremental as it applies existing models to a new benchmark.
The paper tackled the problem of detecting and extracting counterfactual statements in text, achieving first place in exact match and F1 for extraction and second place for detection using RoBERTa models.
This paper describes BUT-FIT's submission at SemEval-2020 Task 5: Modelling Causal Reasoning in Language: Detecting Counterfactuals. The challenge focused on detecting whether a given statement contains a counterfactual (Subtask 1) and extracting both antecedent and consequent parts of the counterfactual from the text (Subtask 2). We experimented with various state-of-the-art language representation models (LRMs). We found RoBERTa LRM to perform the best in both subtasks. We achieved the first place in both exact match and F1 for Subtask 2 and ranked second for Subtask 1.