SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension
Preprint
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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Question Answering through Transfer Learning from Large Fine-grained Supervision Data2017
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data2017
- Natural Language Inference by Tree-Based Convolution and Heuristic Matching2016
- Learning Distributed Representations of Sentences from Unlabelled Data2016