SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension

TL;DR

This paper introduces a neural network model that uses contextualized word vectors from machine translation datasets to improve argument reasoning comprehension, achieving around 70% accuracy on development data.

Contribution

It presents a simple neural architecture leveraging transfer learning with contextualized vectors for argument reasoning, outperforming baselines.

Findings

Achieved approximately 70% accuracy on development set.

Utilized transfer learning from machine translation datasets.

Outperformed several baseline models.

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.