Advances in domain independent linear text segmentation

By Freddy Y. Y. Choi. Applied Natural Language Processing Conference, 2000

769 citations recorded by the source corpus.

This paper describes a method for linear text segmentation which is twice as accurate and over seven times as fast as the state-of-the-art (Reynar, 1998). Inter-sentence similarity is replaced by rank in the local context. Boundary locations are discovered by divisive clustering.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/448aa9b04905e421a8ef6e864c183f7ca6a7bb45

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Articles Summarizing Scientific Articles: Experiments with Relevance and Rhetorical Status (2002, background): “…the distribution of “content-bearing” words and phrases, much less so than the related task of topic segmentation (Morris and Hirst 1991; Hearst 1997; Choi 2000), or Saggion and Lapalme’s (2000) approach to the summarization of scientiﬁc articles, which relies on scientiﬁc concepts and their…”
A Critique and Improvement of an Evaluation Metric for Text Segmentation (2002, methodology): “Some evaluations circumvent this difﬁculty by detecting boundaries in sets of concatenated documents, where there can be no disagreements about the fact of the matter (Reynar, 1994; Choi, 2000); others have several human judges make ratings to produce a ”gold standard”.”
Extractive Summarization of Long Documents by Combining Global and Local Context (2019, background): “In a series of experiments, they show that their model outperform other unsupervised models on natural datasets (except for one synthesized automatically[6]), and that it generalizes well to unseen natural text.”
Discourse Segmentation of Multi-Party Conversation (2003, methodology): “While other relations between lexical items also work as cohesive factors (e.g. between a term and its super-ordinate), the work on linear topic segmentation reporting the most promising results account for term repetitions alone (Choi, 2000; Utiyama and Isahara, 2001).”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Document segmentation: The task of document segmentation is to partition a document into sections, where each section focuses on a different subtopic of the document (Hearst, 1997; Choi, 2000). We may treat the document as a series of blocks, where a block is a sentence or a paragraph. The problem i”
LLM-Enhanced Semantic Text Segmentation (2025, unknown): “As a starting point for evaluating segmentation methods, some studies use a baseline estimate based on random segmentation [8–11].”