3260 papers • 126 benchmarks • 313 datasets
Temporal Relation Classification is the task that is concerned with classifying the temporal relation between a pair of temporal entities (traditional events and temporal expressions). Initial approaches aimed to classify the temporal relation in thirteen relation types that were depicted by James Allen in his seminal work "Maintaining Knowledge about Temporal Intervals". However, due to the ambiguity in the annotation, recent corpora have been limiting the type of relations to a subset of those relations. Notice that although Temporal Relation Classification can be thought of as a subtask of Temporal Relation Extraction, the two tasks can be morphed if one adds a label that indicates the absence of a temporal relation between the entities (e.g. "no_relation" or "vague") to Temporal Relation Classification.
(Image credit: Papersgraph)
These leaderboards are used to track progress in temporal-relation-extraction
Use these libraries to find temporal-relation-extraction models and implementations
No subtasks available.
This work extends the classification model’s task loss with an unsupervised auxiliary loss on the word-embedding level of the model to ensure that the learned word representations contain both task-specific features and more general features learned from the unsuper supervised loss component.
This work addresses the problems of subevent relation extraction and temporal event relation extraction that aim to predict subevent and temporal relations between two given event mentions/triggers in texts and introduces a novel method to better model document-level context with important context sentences for event- Event relation extraction.
A new Syntax-guided Graph Transformer network (SGT) is proposed to mitigate the issue of complex context in-between between events, by explicitly exploiting the connection between two events based on their dependency parsing trees, and automatically locating temporal cues between two Events via a novel syntax-guided attention mechanism.
T tieval, a Python library that provides a concise interface for importing different corpora and is equipped with domain-specific operations that facilitate system evaluation, is developed and the first public release of tieval is presented and its most relevant features are highlighted.
Adding a benchmark result helps the community track progress.