Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction
This work addresses limitations in information extraction for natural language understanding, offering an incremental improvement over prior deep learning systems.
The paper tackled the problem of event temporal relation extraction by addressing issues with hard constraints and biased predictions in neural models, proposing a framework that incorporates probabilistic domain knowledge via Lagrangian Relaxation, which improved baseline models with strong statistical significance on news and clinical datasets.
Extracting event temporal relations is a critical task for information extraction and plays an important role in natural language understanding. Prior systems leverage deep learning and pre-trained language models to improve the performance of the task. However, these systems often suffer from two short-comings: 1) when performing maximum a posteriori (MAP) inference based on neural models, previous systems only used structured knowledge that are assumed to be absolutely correct, i.e., hard constraints; 2) biased predictions on dominant temporal relations when training with a limited amount of data. To address these issues, we propose a framework that enhances deep neural network with distributional constraints constructed by probabilistic domain knowledge. We solve the constrained inference problem via Lagrangian Relaxation and apply it on end-to-end event temporal relation extraction tasks. Experimental results show our framework is able to improve the baseline neural network models with strong statistical significance on two widely used datasets in news and clinical domains.