Tin Kuculo


2018

pdf
TakeLab at SemEval-2018 Task12: Argument Reasoning Comprehension with Skip-Thought Vectors
Ana Brassard | Tin Kuculo | Filip Boltužić | Jan Šnajder
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes our system for the SemEval-2018 Task 12: Argument Reasoning Comprehension Task. We utilize skip-thought vectors, sentence-level distributional vectors inspired by the popular word embeddings and the skip-gram model. We encode preprocessed sentences from the dataset into vectors, then perform a binary supervised classification of the warrant that justifies the use of the reason as support for the claim. We explore a few variations of the model, reaching 54.1% accuracy on the test set, which placed us 16th out of 22 teams participating in the task.