We introduce a top-down approach to discourse parsing that is conceptually
simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By
framing the task as a sequence labelling problem where the goal is to
iteratively segment a document into individual discourse units, we are able to
eliminate the decoder and reduce the search space for splitting points. We
explore both traditional recurrent models and modern pre-trained transformer
models for the task, and additionally introduce a novel dynamic oracle for
top-down parsing. Based on the Full metric, our proposed LSTM model sets a new
state-of-the-art for RST parsing.

本研究介绍了一种自上而下的话语分析方法，该方法的目标是将文档迭代地分段成个体话语单元，这种方法不仅消除了解码器，而且减少了划分点的搜索空间，同时使用了 LSTM 模型，在全指标下达到了最新的 RST 分析结果。

基于序列标注的自顶向下篇章分析

Top-down Discourse Parsing via Sequence Labelling

In recent years, There has been a variety of research on discourse parsing,
particularly RST discourse parsing. Most of the recent work on RST parsing has
focused on implementing new types of features or learning algorithms in order
to improve accuracy, with relatively little focus on efficiency, robustness, or
practical use. Also, most implementations are not widely available. Here, we
describe an RST segmentation and parsing system that adapts models and feature
sets from various previous work, as described below. Its accuracy is near
state-of-the-art, and it was developed to be fast, robust, and practical. For
example, it can process short documents such as news articles or essays in less
than a second.

本文描述了一种 RST 分割和解析系统，该系统可以快速、稳健地处理新闻文章或文章等短文档，并将各种先前工作的模型和特征集进行了适应，其准确性接近于最先进的水平。