A Multi-level Neural Network for Implicit Causality Detection in Web Texts

TL;DR

This paper introduces MCDN, a novel neural network model that combines feature engineering and neural methods to improve implicit causality detection in web texts, leveraging multi-head self-attention and SCRN for better reasoning.

Contribution

The paper presents the first application of Relation Network in causality detection and explicitly models causal reasoning to enhance detection accuracy.

Findings

MCDN outperforms existing causality detection methods.

The model demonstrates robustness and effectiveness in experiments.

Relation Network integration improves causal inference capabilities.

Abstract

Mining causality from text is a complex and crucial natural language understanding task corresponding to the human cognition. Existing studies at its solution can be grouped into two primary categories: feature engineering based and neural model based methods. In this paper, we find that the former has incomplete coverage and inherent errors but provide prior knowledge; while the latter leverages context information but causal inference of which is insufficiency. To handle the limitations, we propose a novel causality detection model named MCDN to explicitly model causal reasoning process, and furthermore, to exploit the advantages of both methods. Specifically, we adopt multi-head self-attention to acquire semantic feature at word level and develop the SCRN to infer causality at segment level. To the best of our knowledge, with regards to the causality tasks, this is the first time that the Relation Network is applied. The experimental results show that: 1) the proposed approach performs prominent performance on causality detection; 2) further analysis manifests the effectiveness and robustness of MCDN.