NLITrans at SemEval-2018 Task 12: Transfer of Semantic Knowledge for Argument Comprehension

TL;DR

This paper presents a transfer learning approach using a pre-trained BiLSTM encoder for argument comprehension, achieving over 64% accuracy and demonstrating the benefits of transfer and regularization techniques in small datasets.

Contribution

It introduces a transfer learning method with a pre-trained sentence encoder for argument reasoning, improving accuracy and dataset efficiency in argument comprehension tasks.

Findings

Transfer learning significantly improves model accuracy.

Independent warrant matching doubles effective dataset size.

Regularization reduces reliance on statistical correlations.

Abstract

The Argument Reasoning Comprehension Task requires significant language understanding and complex reasoning over world knowledge. We focus on transfer of a sentence encoder to bootstrap more complicated models given the small size of the dataset. Our best model uses a pre-trained BiLSTM to encode input sentences, learns task-specific features for the argument and warrants, then performs independent argument-warrant matching. This model achieves mean test set accuracy of 64.43%. Encoder transfer yields a significant gain to our best model over random initialization. Independent warrant matching effectively doubles the size of the dataset and provides additional regularization. We demonstrate that regularization comes from ignoring statistical correlations between warrant features and position. We also report an experiment with our best model that only matches warrants to reasons, ignoring claims. Relatively low performance degradation suggests that our model is not necessarily learning the intended task.