English

An Improved Neural Baseline for Temporal Relation Extraction

Computation and Language 2019-09-04 v1

Abstract

Determining temporal relations (e.g., before or after) between events has been a challenging natural language understanding task, partly due to the difficulty to generate large amounts of high-quality training data. Consequently, neural approaches have not been widely used on it, or showed only moderate improvements. This paper proposes a new neural system that achieves about 10% absolute improvement in accuracy over the previous best system (25% error reduction) on two benchmark datasets. The proposed system is trained on the state-of-the-art MATRES dataset and applies contextualized word embeddings, a Siamese encoder of a temporal common sense knowledge base, and global inference via integer linear programming (ILP). We suggest that the new approach could serve as a strong baseline for future research in this area.

Keywords

Cite

@article{arxiv.1909.00429,
  title  = {An Improved Neural Baseline for Temporal Relation Extraction},
  author = {Qiang Ning and Sanjay Subramanian and Dan Roth},
  journal= {arXiv preprint arXiv:1909.00429},
  year   = {2019}
}

Comments

This short paper is accepted to EMNLP 2019; appendix included

R2 v1 2026-06-23T11:02:36.599Z