TakeLab at SemEval-2018 Task12: Argument Reasoning Comprehension with Skip-Thought Vectors

Ana Brassard, Tin Kuculo, Filip Boltužić, Jan Šnajder


Abstract
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.
Anthology ID:
S18-1192
Volume:
Proceedings of the 12th International Workshop on Semantic Evaluation
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1133–1136
Language:
URL:
https://aclanthology.org/S18-1192
DOI:
10.18653/v1/S18-1192
Bibkey:
Cite (ACL):
Ana Brassard, Tin Kuculo, Filip Boltužić, and Jan Šnajder. 2018. TakeLab at SemEval-2018 Task12: Argument Reasoning Comprehension with Skip-Thought Vectors. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 1133–1136, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
TakeLab at SemEval-2018 Task12: Argument Reasoning Comprehension with Skip-Thought Vectors (Brassard et al., SemEval 2018)
Copy Citation:
PDF:
https://aclanthology.org/S18-1192.pdf