Towards Domain-Independent Supervised Discourse Parsing Through Gradient Boosting

Abstract: Discourse analysis and discourse parsing have shown great impact on many important problems in the field of NLP. Given the direct impact of discourse annotations on model performance and interpretability, robustly extracting discourse structures from arbitrary documents is a key task to further improve computational models in NLP. To this end, we present a new, supervised paradigm directly tackling the domain adaptation issue in discourse parsing. Specifically, we introduce the first fully supervised discourse parser designed to alleviate the domain dependency through a staged model of weak classifiers by introducing the gradient boosting framework.