Despite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet limited. In this paper, we examine and model some of the factors associated with parsing difficulties in previous work: the existence of implicit discourse relations, challenges in identifying long-distance relations, out-of-vocabulary items, and more. In order to assess the relative importance of these variables, we also release two annotated English test-sets with explicit correct and distracting discourse markers associated with gold standard RST relations. Our results show that as in shallow discourse parsing, the explicit/implicit distinction plays a role, but that long-distance dependencies are the main challenge, while lack of lexical overlap is less of a problem, at least for in-domain parsing. Our final model is able to predict where errors will occur with an accuracy of 76.3% for the bottom-up parser and 76.6% for the top-down parser.

翻译：尽管自然语言处理（NLP）近期取得了进展，但在修辞结构理论框架下进行层级篇章解析仍具挑战性，且我们对其中原因的理解尚有限。本文考察并建模了前人研究中与解析困难相关的若干因素：隐性篇章关系的存在、长距离关系识别的难题、词汇表外词汇等。为评估这些变量的相对重要性，我们还发布了两个带标注的英文测试集，其中包含与黄金标准RST关系对应的显性正确及干扰性篇章标记。结果表明，与浅层篇章解析类似，显性/隐性区分具有一定影响，但长距离依存是主要挑战，而词汇重叠不足的问题相对较小（至少对领域内解析而言如此）。我们的最终模型能以76.3%（自底向上解析器）和76.6%（自顶向下解析器）的准确率预测错误发生位置。