# Classification and Clustering of Arguments with Contextualized Word Embeddings

## TL;DR

This paper demonstrates how to use contextualized word embeddings like ELMo and BERT to classify and cluster arguments in open-domain argument search, achieving state-of-the-art results on multiple datasets.

## Contribution

It introduces a novel application of contextualized embeddings for argument classification and clustering, with a new pre-training step for argument clustering tasks.

## Key findings

- 20.8% improvement on UKP Sentential Argument Mining Corpus
- 7.4% improvement on IBM Debater Evidence Sentences dataset
- Significant gains in argument clustering performance on new datasets

## Abstract

We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater - Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument clustering, we propose a pre-training step which improves by 7.8 percentage points over strong baselines on a novel dataset, and by 12.3 percentage points for the Argument Facet Similarity (AFS) Corpus.