Tree-Constrained Graph Neural Networks For Argument Mining
This addresses argument mining for natural language processing researchers, presenting an incremental improvement through a hybrid method.
The authors tackled argument mining by proposing a novel Graph Neural Network architecture that incorporates tree fragment similarity through regularization constraints and pooling mechanisms, achieving competitive performance with state-of-the-art techniques on multiple sentence classification tasks across several corpora.
We propose a novel architecture for Graph Neural Networks that is inspired by the idea behind Tree Kernels of measuring similarity between trees by taking into account their common substructures, named fragments. By imposing a series of regularization constraints to the learning problem, we exploit a pooling mechanism that incorporates such notion of fragments within the node soft assignment function that produces the embeddings. We present an extensive experimental evaluation on a collection of sentence classification tasks conducted on several argument mining corpora, showing that the proposed approach performs well with respect to state-of-the-art techniques.