Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction
This work addresses the challenge of error propagation in pipeline systems for event and temporal relation extraction, offering a joint approach that benefits researchers in natural language processing.
The paper tackles the problem of jointly extracting events and their temporal relations by proposing a model with shared representation learning and structured prediction, resulting in end-to-end F1 improvements of 10% and 6.8% on two benchmark datasets.
We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction. The proposed method has two advantages over existing work. First, it improves event representation by allowing the event and relation modules to share the same contextualized embeddings and neural representation learner. Second, it avoids error propagation in the conventional pipeline systems by leveraging structured inference and learning methods to assign both the event labels and the temporal relation labels jointly. Experiments show that the proposed method can improve both event extraction and temporal relation extraction over state-of-the-art systems, with the end-to-end F1 improved by 10% and 6.8% on two benchmark datasets respectively.