Event ordering with a generalized model for sieve prediction ranking (Natural Language Processing, 2017) 

This paper improves on several aspects of a sieve-based event ordering architecture, CAEVO (Chambers et al., 2014), which creates globally consistent temporal rela- tions between events and time expressions. First, we examine the usage of word em- beddings and semantic role features. With the incorporation of these new features, we demonstrate a 5% relative F1 gain over our replicated version of CAEVO. Second, we reformulate the architecture’s sieve-based inference algorithm as a prediction rerank- ing method that approximately optimizes a scoring function computed using classifier precisions. Within this prediction rerank- ing framework, we propose an alternative scoring function, showing an 8.8% relative gain over the original CAEVO. We further include an in-depth analysis of one of the main datasets that is used to evaluate tem- poral classifiers, and we show that in spite of the density of this corpus, there is still a danger of overfitting. While this paper focuses on temporal ordering, its results are applicable to other areas that use sieve- based architectures.