Key Point Matching with Transformers
Emanuele Cosenza · 2021
Key point analysis (KPA) has been proposed as a way to summarize arguments with shortsized pieces of text termed key points.This work aims at describing a solution for the Track 1 of the KPA 2021 shared task, analyzing different methodologies for the specific problem of key point matching, which consists in finding a reasonable mapping from arguments to key points.The analysis will focus on transformer based architectures, experimentally investigating the effectiveness of variants specifically tailored to the task.