ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling
This work addresses a specific NLP challenge for researchers and practitioners in computational semantics, but it is incremental as it applies existing transformer methods to a new task.
The paper tackled the problem of detecting counterfactual statements and extracting their antecedent and consequence in natural language processing, achieving third place in both subtasks of SemEval-2020 Task 5 using a system based on pre-trained transformers.
ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting counterfactual statements and detecting antecedent and consequence. This paper describes our system which is based on pre-trained transformers. For the first subtask, we train several transformer-based classifiers for detecting counterfactual statements. For the second subtask, we formulate antecedent and consequence extraction as a query-based question answering problem. The two subsystems both achieved third place in the evaluation. Our system is openly released at https://github.com/casnlu/ISCAS-SemEval2020Task5.