Towards Domain-Independent Supervised Discourse Parsing Through Gradient Boosting

TL;DR

This paper introduces a new supervised discourse parser that uses gradient boosting to reduce domain dependency, improving the robustness and adaptability of discourse parsing across different document types in NLP.

Contribution

It presents the first fully supervised discourse parser leveraging gradient boosting to address domain adaptation challenges in discourse parsing.

Findings

Demonstrates improved domain robustness in discourse parsing.

Introduces a staged model of weak classifiers using gradient boosting.

Enhances model interpretability and performance across diverse domains.

Abstract

Discourse analysis and discourse parsing have shown great impact on many important problems in the field of Natural Language Processing (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.