Integer-Programming Ensemble of Temporal-Relations Classifiers
This work addresses the problem of temporal relation classification for NLP researchers and practitioners, offering an incremental improvement through ensemble techniques.
The paper tackled the challenge of extracting and understanding temporal events and relations in natural language processing by proposing an ensemble method that reconciles multiple classifier outputs using integer programming to improve global consistency. The result showed improvements over the best individual results in SemEval-2013 TempEval-3 and SemEval-2016 Task 12 benchmarks.
The extraction and understanding of temporal events and their relations are major challenges in natural language processing. Processing text on a sentence-by-sentence or expression-by-expression basis often fails, in part due to the challenge of capturing the global consistency of the text. We present an ensemble method, which reconciles the outputs of multiple classifiers of temporal expressions across the text using integer programming. Computational experiments show that the ensemble improves upon the best individual results from two recent challenges, SemEval-2013 TempEval-3 (Temporal Annotation) and SemEval-2016 Task 12 (Clinical TempEval).