Joint Reasoning for Temporal and Causal Relations
This work addresses a fundamental natural language understanding task for AI researchers, but it is incremental as it builds on existing methods to study temporal and causal relations jointly.
The paper tackled the problem of jointly extracting temporal and causal relations from text by proposing a joint inference framework using constrained conditional models and integer linear programming, resulting in statistically significant improvements in extraction accuracy for both relation types.
Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must be before its effect in time, temporal and causal relations are closely related and one relation even dictates the other one in many cases. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints inherently in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.