Abstract
We present a novel neural architecture for the Argument Reasoning Comprehension task of SemEval 2018. It is a simple neural network consisting of three parts, collectively judging whether the logic built on a set of given sentences (a claim, reason, and warrant) is plausible or not. The model utilizes contextualized word vectors pre-trained on large machine translation (MT) datasets as a form of transfer learning, which can help to mitigate the lack of training data. Quantitative analysis shows that simply leveraging LSTMs trained on MT datasets outperforms several baselines and non-transferred models, achieving accuracies of about 70% on the development set and about 60% on the test set.- Anthology ID:
- S18-1182
- Volume:
- Proceedings of the 12th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Venues:
- SemEval | *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1083–1088
- Language:
- URL:
- https://aclanthology.org/S18-1182
- DOI:
- 10.18653/v1/S18-1182
- Cite (ACL):
- Taeuk Kim, Jihun Choi, and Sang-goo Lee. 2018. SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 1083–1088, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension (Kim et al., SemEval-*SEM 2018)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/S18-1182.pdf
- Code
- galsang/SemEval2018-task12
- Data
- SNLI