Two-Phased Event Causality Acquisition: Coupling the Boundary Identification and Argument Identification Approaches
Yanan Cao, Cungen Cao, Jingzun Zhang, Wenjia Niu · Lecture notes in computer science · 2015
Event causality is indispensable for knowledge-driven intelligent systems. In this paper, we propose a supervised method of extracting event causalities such as forest is cut down $$\rightarrow $$ forest is destroyed from web text. While relation identification using lexico-syntactic patterns (LSPs) is not novel, it is still challenging to extract the event expressions with necessary arguments from identified causality mentions. To address this issue, our method divides event-pair extraction into two phases: event boundary identification and missing argument identification. In the first phase, we propose a Naive Baysian probability method to identify the boundary of causal events, and extract the corresponding text fragments as event expressions. Secondly, we learn a multi-class decision tree (LADTree) to identify the missing argument for each incomplete event. Experimental results showed the good effectiveness of our approach on a large-scale open corpus.