Multi-Paragraph Segmentation of Expository Text
arXiv:cmp-lg/9406037
Abstract
This paper describes TextTiling, an algorithm for partitioning expository texts into coherent multi-paragraph discourse units which reflect the subtopic structure of the texts. The algorithm uses domain-independent lexical frequency and distribution information to recognize the interactions of multiple simultaneous themes. Two fully-implemented versions of the algorithm are described and shown to produce segmentation that corresponds well to human judgments of the major subtopic boundaries of thirteen lengthy texts.
To Appear in ACL '94 Proceedings; 8 pages POSTSCRIPT format
Cited by in corpus (24)
- Advances in domain independent linear text segmentation
- Inferring Strategies for Sentence Ordering in Multidocument News Summarization
- Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization
- Integrating Prosodic and Lexical Cues for Automatic Topic Segmentation
- Automatic summarising: factors and directions
- Linear Segmentation and Segment Significance
- Text Segmentation Using Exponential Models
- Segmentation of Expository Texts by Hierarchical Agglomerative Clustering
- The Structure of Narrative: the Case of Film Scripts
- Designing Statistical Language Learners: Experiments on Noun Compounds
- Content Modeling Using Latent Permutations
- OntoSeg: a Novel Approach to Text Segmentation using Ontological Similarity
- Practical Approach to Knowledge-based Question Answering with Natural Language Understanding and Advanced Reasoning
- Computational Approach to Anaphora Resolution in Spanish Dialogues
- Optimal Multi-Paragraph Text Segmentation by Dynamic Programming
- Tag Clouds for Displaying Semantics: The Case of Filmscripts
- Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
- Centering in-the-large: Computing referential discourse segments
- Automated text summarisation and evidence-based medicine: A survey of two domains
- A Scalable Video Search Engine Based on Audio Content Indexing and Topic Segmentation
- Cue Phrase Classification Using Machine Learning
- A Dynamic Programming Algorithm for the Segmentation of Greek Texts
- Chapter Captor: Text Segmentation in Novels
- Thematic Annotation: extracting concepts out of documents