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

By Timothy Niven, Hung-Yu kao. 2018

4 citations recorded by the source corpus.

The Argument Reasoning Comprehension Task is a difficult challenge requiring significant language understanding and complex reasoning over world knowledge. We focus on transfer of a sentence encoder to bootstrap more complicated architectures 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 61.31%. Encoder transfer yields a significant gain to our best model over random initialization. Sharing parameters for independent warrant evaluation provides regularization and effectively doubles the size of the dataset. We demonstrate that regularization comes from ignoring statistical correlations between warrant positions. We also report an experiment with our best model that only matches warrants to reasons, ignoring claims. Performance is still competitive, suggesting that our model is not necessarily learning the intended task.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Timothy Niven
2. Hung-Yu kao
3. Samuel R. Bowman
4. Zhiyong Lu
5. Yejin Choi

In Computer Vision and Pattern Recognition

1. Timothy Niven
2. Hung-Yu kao

In Natural Language Processing

1. Timothy Niven
2. Hung-Yu kao
3. Samuel R. Bowman
4. Yejin Choi

Citations in the corpus

• Probing Neural Network Comprehension of Natural Language Arguments (2019, methodology): “The most successful previous work on ARCT (Choi and Lee, 2018; Zhao et al., 2018; Niven and Kao, 2018) involved transfer learning from Natural Language Inference (NLI) datasets (Bowman et al., 2015; Williams et al., 2017), and utilized effective NLI models such as ESIM (Chen et al., 2016) and…”