Towards Causal Explanation Detection with Pyramid Salient-Aware Network

TL;DR

This paper introduces the Pyramid Salient-Aware Network (PSAN), a novel model designed to detect causal explanations in messages by capturing salient semantics at both word and discourse levels, improving accuracy over previous methods.

Contribution

The paper proposes PSAN, a new neural network architecture that combines bottom-up and top-down salient networks for causal explanation detection.

Findings

PSAN outperforms previous state-of-the-art by 1.8% F1 score.

The model effectively captures salient semantics at multiple discourse levels.

Experimental results validate the effectiveness of the pyramid salient-aware approach.

Abstract

Causal explanation analysis (CEA) can assist us to understand the reasons behind daily events, which has been found very helpful for understanding the coherence of messages. In this paper, we focus on Causal Explanation Detection, an important subtask of causal explanation analysis, which determines whether a causal explanation exists in one message. We design a Pyramid Salient-Aware Network (PSAN) to detect causal explanations on messages. PSAN can assist in causal explanation detection via capturing the salient semantics of discourses contained in their keywords with a bottom graph-based word-level salient network. Furthermore, PSAN can modify the dominance of discourses via a top attention-based discourse-level salient network to enhance explanatory semantics of messages. The experiments on the commonly used dataset of CEA shows that the PSAN outperforms the state-of-the-art method by 1.8% F1 value on the Causal Explanation Detection task.