Segmentation en phrases : ouvrez les guillemets sans perdre le fil

TL;DR

This paper introduces a graph cascade method for sentence segmentation in XML documents, effectively handling nested sentences, quotations, and lists, with performance evaluation against 2019 benchmarks.

Contribution

The paper proposes a novel graph cascade approach for complex sentence segmentation, addressing nested structures and punctuation challenges in XML documents.

Findings

Effective segmentation of nested sentences and quotations

Improved performance over 2019 benchmarks

Robust handling of parentheses and colons

Abstract

This paper presents a graph cascade for sentence segmentation of XML documents. Our proposal offers sentences inside sentences for cases introduced by quotation marks and hyphens, and also pays particular attention to situations involving incises introduced by parentheses and lists introduced by colons. We present how the tool works and compare the results obtained with those available in 2019 on the same dataset, together with an evaluation of the system's performance on a test corpus