Linear Segmentation and Segment Significance

TL;DR

This paper introduces a novel method for segmenting documents into discourse units and identifying their functions using noun phrase retrieval, zero-sum weighting, and term distribution analysis, achieving improved precision and recall.

Contribution

The paper proposes a new segmentation and segment function identification method that outperforms previous approaches in accuracy.

Findings

Higher precision and recall in segment identification

Effective use of noun phrases and term distribution for segmentation

Demonstrated improvement over earlier methods

Abstract

We present a new method for discovering a segmental discourse structure of a document while categorizing segment function. We demonstrate how retrieval of noun phrases and pronominal forms, along with a zero-sum weighting scheme, determines topicalized segmentation. Futhermore, we use term distribution to aid in identifying the role that the segment performs in the document. Finally, we present results of evaluation in terms of precision and recall which surpass earlier approaches.