Team Enigma at ArgMining-EMNLP 2021: Leveraging Pre-trained Language Models for Key Point Matching

TL;DR

This paper describes Team Enigma's approach to key point matching in argument analysis using pre-trained language models, achieving high accuracy and securing 5th place in the ArgMining-EMNLP 2021 shared task.

Contribution

The authors combined pre-trained language models with additional data and features to improve argument-keypoint matching performance.

Findings

Achieved mAP strict score of 0.872 in evaluation

Secured 5th place on the leaderboard

Post-evaluation scores improved to 0.921 mAP strict

Abstract

We present the system description for our submission towards the Key Point Analysis Shared Task at ArgMining 2021. Track 1 of the shared task requires participants to develop methods to predict the match score between each pair of arguments and keypoints, provided they belong to the same topic under the same stance. We leveraged existing state of the art pre-trained language models along with incorporating additional data and features extracted from the inputs (topics, key points, and arguments) to improve performance. We were able to achieve mAP strict and mAP relaxed score of 0.872 and 0.966 respectively in the evaluation phase, securing 5th place on the leaderboard. In the post evaluation phase, we achieved a mAP strict and mAP relaxed score of 0.921 and 0.982 respectively. All the codes to generate reproducible results on our models are available on Github.