A Structured Learning Approach to Temporal Relation Extraction
This addresses a key problem in natural language understanding for researchers and practitioners, though it appears incremental as it builds on existing methods by incorporating dependencies.
The paper tackles the challenge of identifying temporal relations between events in natural language by proposing a structured learning approach that accounts for dependencies among events, resulting in significant improvements on two commonly used datasets.
Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively identifying temporal relations between events is a challenging problem even for human annotators. This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. As a byproduct, this provides a new perspective on handling missing relations, a known issue that hurts existing methods. As we show, the proposed approach results in significant improvements on the two commonly used data sets for this problem.