@inproceedings{c590c49b6fdf488f940879072928e94a,
title = "Text segmentation as a supervised learning task",
abstract = "Text segmentation, the task of dividing a document into contiguous segments based on its semantic structure, is a longstanding challenge in language understanding. Previous work on text segmentation focused on unsupervised methods such as clustering or graph search, due to the paucity in labeled data. In this work, we formulate text segmentation as a supervised learning problem, and present a large new dataset for text segmentation that is automatically extracted and labeled from Wikipedia. Moreover, we develop a segmentation model based on this dataset and show that it generalizes well to unseen natural text.",
author = "Omri Koshorek and Adir Cohen and Noam Mor and Michael Rotman and Jonathan Berant",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics.; 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",
year = "2018",
language = "الإنجليزيّة",
series = "NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "469--473",
booktitle = "Short Papers",
address = "الولايات المتّحدة",
}