Fine-Grained Temporal Relation Extraction
Computation and Language
2019-06-05 v2
Abstract
We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real-valued scales. We use this framework to construct the largest temporal relations dataset to date, covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to train models for jointly predicting fine-grained temporal relations and event durations. We report strong results on our data and show the efficacy of a transfer-learning approach for predicting categorical relations.
Cite
@article{arxiv.1902.01390,
title = {Fine-Grained Temporal Relation Extraction},
author = {Siddharth Vashishtha and Benjamin Van Durme and Aaron Steven White},
journal= {arXiv preprint arXiv:1902.01390},
year = {2019}
}
Comments
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), Florence, Italy, July 29-31, 2019