Attention, intentions, and the structure of discourse
Computational Linguistics
Word association norms, mutual information, and lexicography
Computational Linguistics
Lexical cohesion computed by thesaural relations as an indicator of the structure of text
Computational Linguistics
TextTiling: segmenting text into multi-paragraph subtopic passages
Computational Linguistics
Text segmentation based on similarity between words
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
A grammatico-statistical approach to discourse partitioning
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
INTEX: a corpus processing system
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Text Segmentation into Paragraphs Based on Local Text Cohesion
TSD '01 Proceedings of the 4th International Conference on Text, Speech and Dialogue
A bootstrapping approach for robust topic analysis
Natural Language Engineering
Thematic segmentation of meetings through document/speech alignment
Proceedings of the 12th annual ACM international conference on Multimedia
Using bi-modal alignment and clustering techniques for documents and speech thematic segmentations
Proceedings of the thirteenth ACM international conference on Information and knowledge management
Constraining the use of general lexical resources for automatic hyperlink generation
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Hi-index | 0.00 |
To segment texts in thematic units, we present here how a basic principle relying on word distribution can be applied on different kind of texts. We start from an existing method well adapted for scientific texts, and we propose its adaptation to other kinds of texts by using semantic links between words. These relations are found in a lexical network, automatically built from a large corpus. We will compare their results and give criteria to choose the more suitable method according to text characteristics.