Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
This work addresses the issue of unreliable temporal relation extraction for natural language processing applications, representing an incremental improvement with specific gains.
The paper tackled the problem of improving faithfulness in event temporal relation extraction by mitigating training biases and providing uncertainty estimation, resulting in more faithful extractions compared to state-of-the-art methods, especially under distribution shifts.
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description. To achieve this, we propose to conduct counterfactual analysis to attenuate the effects of two significant types of training biases: the event trigger bias and the frequent label bias. We also add tense information into event representations to explicitly place an emphasis on the contextual description. The second perspective is to provide proper uncertainty estimation and abstain from extraction when no relation is described in the text. By parameterization of Dirichlet Prior over the model-predicted categorical distribution, we improve the model estimates of the correctness likelihood and make TempRel predictions more selective. We also employ temperature scaling to recalibrate the model confidence measure after bias mitigation. Through experimental analysis on MATRES, MATRES-DS, and TDDiscourse, we demonstrate that our model extracts TempRel and timelines more faithfully compared to SOTA methods, especially under distribution shifts.