Year: 2020
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Zhao, Xinyu, Lin, Shih-ting, Durrett, Greg
Institution: The University of Texas at Austin
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G4713059963
OpenAlex ID: W3094375194