Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events
This addresses the challenge of temporal ordering in natural language processing, which is incremental as it builds on existing pretrained models and datasets.
The paper tackles the problem of ordering events by predicting temporal relations between event pairs in text, achieving a new state-of-the-art on the MATRES dataset.
In this paper, we propose a neural architecture and a set of training methods for ordering events by predicting temporal relations. Our proposed models receive a pair of events within a span of text as input and they identify temporal relations (Before, After, Equal, Vague) between them. Given that a key challenge with this task is the scarcity of annotated data, our models rely on either pretrained representations (i.e. RoBERTa, BERT or ELMo), transfer and multi-task learning (by leveraging complementary datasets), and self-training techniques. Experiments on the MATRES dataset of English documents establish a new state-of-the-art on this task.