Search papers, labs, and topics across Lattice.
This paper tackles the challenging task of fine-grained temporal relation classification, aiming to classify the full set of interval relations between temporal entities. They introduce "Interval from Point," a novel approach that first classifies point relations between the endpoints of temporal entities and then decodes these into interval relations. Experiments on the TempEval-3 dataset demonstrate the effectiveness of this method, achieving a new state-of-the-art temporal awareness score of 70.1%.
Classifying temporal relations is easier when you break it down: predicting relationships between endpoints first unlocks state-of-the-art performance on a challenging benchmark.
Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text. Despite recent advancements in natural language processing, temporal relation classification remains a considerable challenge. Early attempts framed this task using a comprehensive set of temporal relations between events and temporal expressions. However, due to the task complexity, datasets have been progressively simplified, leading recent approaches to focus on the relations between event pairs and to use only a subset of relations. In this work, we revisit the broader goal of classifying interval relations between temporal entities by considering the full set of relations that can hold between two time intervals. The proposed approach, Interval from Point, involves first classifying the point relations between the endpoints of the temporal entities and then decoding these point relations into an interval relation. Evaluation on the TempEval-3 dataset shows that this approach can yield effective results, achieving a temporal awareness score of $70.1$ percent, a new state-of-the-art on this benchmark.