# ESURF: Simple and Effective EDU Segmentation

arXiv: https://arxiv.org/abs/2501.07723 · HTML: https://mlsanity.com/paper/2501.07723/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2025.

## Abstract (arXiv)

Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features, using random forest classification. We show that the method, despite its simplicity, outperforms other methods both for segmentation and within a state of the art discourse parser. This indicates the importance of such features for identifying basic discourse elements, pointing towards potentially more training-efficient methods for discourse analysis.