Classification and Clustering of Arguments with Contextualized Word Embeddings
This work addresses the challenge of open-domain argument search for applications like debate analysis, though it is incremental as it applies existing embedding methods to a specific domain.
The paper tackled the problem of classifying and clustering topic-dependent arguments using contextualized word embeddings like ELMo and BERT, achieving improvements such as 20.8 percentage points on the UKP Sentential Argument Mining Corpus and 7.4 percentage points on the IBM Debater dataset for classification, and 7.8 to 12.3 percentage points for clustering tasks.
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.