DMON: A Simple yet Effective Approach for Argument Structure Learning
This work addresses the challenging task of ASL, which is important for structuring documents in fields like medical, commercial, and scientific domains, but it appears incremental as it builds on existing methods with a novel hybrid approach.
The paper tackles the problem of argument structure learning (ASL) by predicting relations between arguments to structure documents, and it introduces DMON, a dual-tower multi-scale convolutional neural network that outperforms state-of-the-art models on three different-domain datasets.
Argument structure learning~(ASL) entails predicting relations between arguments. Because it can structure a document to facilitate its understanding, it has been widely applied in many fields~(medical, commercial, and scientific domains). Despite its broad utilization, ASL remains a challenging task because it involves examining the complex relationships between the sentences in a potentially unstructured discourse. To resolve this problem, we have developed a simple yet effective approach called Dual-tower Multi-scale cOnvolution neural Network~(DMON) for the ASL task. Specifically, we organize arguments into a relationship matrix that together with the argument embeddings forms a relationship tensor and design a mechanism to capture relations with contextual arguments. Experimental results on three different-domain argument mining datasets demonstrate that our framework outperforms state-of-the-art models. The code is available at https://github.com/VRCMF/DMON.git .