Classification and Clustering of Arguments with Contextualized Word Embeddings

Nils Reimers, Benjamin Schiller, Tilman Beck, Johannes Daxenberger, Christian Stab +1 more
6/24/2019
cs.CL

Official code: UKPLab/acl2019-BERT-argument-classification-and-clustering (85 stars, Apache-2.0, last commit 2020-12-15).

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.

View on arXivView PDF

Code Implementations(1)

UKPLab/acl2019-BERT-argument-classification-and-clusteringOfficial100%
Apache-2.0
8534Shell, PythonMay 16, 20195 years agoApache-2.0

Similar Papers

Explainable Topic-Enhanced Argument Mining from Heterogeneous Sources

81% match2023

PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search

80% match1 repo72022

Multi-Task Learning Improves Performance In Deep Argument Mining Models

78% match2023

Topic Ontologies for Arguments

78% match2023

AutoAM: An End-To-End Neural Model for Automatic and Universal Argument Mining

77% match2023

Open Knowledge Base Canonicalization with Multi-task Learning

77% match2024

Cite this paper

@article{reimers2019classification,
  title  = {Classification and Clustering of Arguments with Contextualized Word Embeddings},
  author = {Nils Reimers and Benjamin Schiller and Tilman Beck and Johannes Daxenberger and Christian Stab and Iryna Gurevych},
  year   = {2019},
  eprint = {1906.09821},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1906.09821}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1906.09821.svg)](https://codeofpaper.com/paper/1906.09821)

Discussion