OPT: Oslo-Potsdam-Teesside Pipelining Rules, Rankers, and Classifier Ensembles for Shallow Discourse Parsing

摘要

The OPT submission to the Shared Task of the 2016 Conference on Natural Language Learning (CoNLL) implements a 'classic' pipeline architecture, combining binary classification of (candidate) explicit connectives, heuristic rules for non-explicit discourse relations, ranking and 'editing' of syntactic constituents for argument identification, and an ensemble of classifiers to assign discourse senses. With an end-to-end performance of 27.77 F_1 on the English 'blind' test data, our system advances the previous state of the art (Wang & Lan, 2015) by close to four F_1 points, with particularly good results for the argument identification sub-tasks.