Advances in domain independent linear text segmentation

Abstract

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.

8 pages, 8 figures. To appear in Proceedings of NAACL00, Seattle. Software and experiment packages available from author's homepage: http://www.cs.man.ac.uk/~choif

References in corpus (4)

• Multi-Paragraph Segmentation of Expository Text
• Text Segmentation Using Exponential Models
• Linear Segmentation and Segment Significance
• Segmentation of Expository Texts by Hierarchical Agglomerative Clustering

Cited by in corpus (26)

• From Frequency to Meaning: Vector Space Models of Semantics
• The Structure of Narrative: the Case of Film Scripts
• Structural Text Segmentation of Legal Documents
• OntoSeg: a Novel Approach to Text Segmentation using Ontological Similarity
• Summarizing Decisions in Spoken Meetings
• Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization
• Improving Context Modeling in Neural Topic Segmentation
• Common Sense Knowledge, Ontology and Text Mining for Implicit Requirements
• Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization
• Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
• Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation
• Improving automated segmentation of radio shows with audio embeddings
• BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation
• Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation
• Segmenting Messy Text: Detecting Boundaries in Text Derived from Historical Newspaper Images
• Text Segmentation using Named Entity Recognition and Co-reference Resolution in English and Greek Texts
• Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence
• Analyse spectrale des textes: détection automatique des frontières de langue et de discours
• Segmentation and Nodal Points in Narrative: Study of Multiple Variations of a Ballad
• SECTOR: A Neural Model for Coherent Topic Segmentation and Classification
• A Hybrid Framework for Topic Structure using Laughter Occurrences
• Chapter Captor: Text Segmentation in Novels
• A Dynamic Programming Algorithm for the Segmentation of Greek Texts
• Learning Constraints and Descriptive Segmentation for Subevent Detection
• Automatically Segmenting Oral History Transcripts
• A Model Approach to Build Basic Ontology