Effective Distant Supervision for Temporal Relation Extraction

By Xinyu Zhao, Shih-Ting Lin, Greg Durrett. 2020

24 citations recorded by the source corpus.

A principal barrier to training temporal relation extraction models in new domains is the lack of varied, high quality examples and the challenge of collecting more. We present a method of automatically collecting distantly-supervised examples of temporal relations. We scrape and automatically label event pairs where the temporal relations are made explicit in text, then mask out those explicit cues, forcing a model trained on this data to learn other signals. We demonstrate that a pre-trained Transformer model is able to transfer from the weakly labeled examples to human-annotated benchmarks in both zero-shot and few-shot settings, and that the masking scheme is important in improving generalization.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiang Ren
2. Nanyun Peng
3. Rujun Han
4. Jie Yang
5. Emily Sheng
6. Shuaicheng Zhang
7. Yi Luan
8. Liyuan Wang

Citations in the corpus

• ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning (2020, background): “Zhou et al. (2020a) and Zhao et al. (2020) are two recent works that attempt to incorporate event temporal knowledge in PTLMs.”