# Two-pass Discourse Segmentation with Pairing and Global Features

arXiv: https://arxiv.org/abs/1407.8215 · HTML: https://mlsanity.com/paper/1407.8215/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2014.

## Built on by (most cited first, 2 of 2)

- [Persian Rhetorical Structure Theory](https://mlsanity.com/paper/2106.13833/) (2021)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)

## Abstract (arXiv)

Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing features, which are centered on a pair of adjacent tokens in the sentence, by equally taking into account the information from both tokens. Moreover, we propose a novel set of global features, which encode characteristics of the segmentation as a whole, once we have an initial segmentation. We show that both the pairing and global features are useful on their own, and their combination achieved an F1 of 92.6% of identifying in-sentence discourse boundaries, which is a 17.8% error-rate reduction over the state-of-the-art performance, approaching 95% of human performance. In addition, similar improvement is observed across different classification frameworks.