We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real valued scales for the purpose of constructing document-level event timelines.

Using our framework, we construct the largest temporal relation dataset to date, and use it to train a variety of neural models to jointly predict finegrained (real-valued) temporal relations and event durations, showing not only that our models obtain strong results on our dataset, the representations they learn can be straightforwardly transferred to the standard categorical relation datasets with competitive performance.


Train Dev Test Download Citation
59593 16914 15411 v1 (zip) Vashishtha et al. 2019


Vashishtha, Siddharth, Benjamin Van Durme, and Aaron Steven White. 2019. Fine-Grained Temporal Relation Extraction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2906–2919. Florence, Italy: Association for Computational Linguistics. [pdf, doi, bib]


Siddharth Vashishtha bio photo
Siddharth Vashishtha
Aaron Steven White bio photo
Aaron Steven White
Benjamin Van Durme bio photo
Benjamin Van Durme