Generating Event Causality Hypotheses through Semantic Relations

Abstract

Event causality knowledge is indispensable for intelligent natural language understanding. The problem is that any method for extracting event causalities from text is insufficient; it is likely that some event causalities that we can recognize in this world are not written in a corpus, no matter its size. We propose a method of hypothesizing unseen event causalities from known event causalities extracted from the web by the semantic relations between nouns. For example, our method can hypothesize "deploy a security camera" -> "avoid crimes" from "deploy a mosquito net" -> "avoid malaria" through semantic relation . Our experiments show that, from 2.4 million event causalities extracted from the web, our method generated more than 300,000 hypotheses, which were not in the input, with 70% precision. We also show that our method outperforms a state-of-the-art hypothesis generation method.

Improving Event Causality Recognition with Multiple Background Knowledge Sources Using Multi-Column Convolutional Neural Networks

“…We empirically showed that the combination of MCNNs and such background knowledge can significantly improve performance over the previous state-of-the-art method. In future work, we plan to apply our proposed method to event causality hypothesis generation (Hashimoto et al 2015).…”

Construction and analysis of knowledge graphs for multi‐source heterogeneous data of soil pollution

“…Because the entity relationships in the contaminated site domain are relatively fixed, this paper adopts a pattern‐matching‐based approach for the extraction of contaminated site entity relationships (Lample et al, 2016). The method based on pattern matching is to construct lexical or semantic‐based pattern sets and store them based on existing relationship instances, guided by domain prior knowledge, and then match the elements in natural language processed statements with the pattern sets to determine entity relationships (Hashimoto et al, 2015; Zhao et al, 2017).…”