@inproceedings{42a9e2dddd20404b8213e4cccc86711d,
title = "A phrase mining framework for recursive construction of a topical hierarchy",
abstract = "A high quality hierarchical organization of the concepts in a dataset at different levels of granularity has many valuable applications such as search, summarization, and content browsing. In this paper we propose an algorithm for recursively constructing a hierarchy of topics from a collection of content-representative documents. We characterize each topic in the hierarchy by an integrated ranked list of mixed-length phrases. Our mining framework is based on a phrase-centric view for clustering, extracting, and ranking topical phrases. Experiments with datasets from different domains illustrate our ability to generate hierarchies of high quality topics represented by meaningful phrases.",
keywords = "Keyphrase extraction, Keyphrase ranking, Network analysis, Ontology learning, Topic modeling",
author = "Chi Wang and Marina Danilevsky and Nihit Desai and Yinan Zhang and Phuong Nguyen and Thrivikrama Taula and Jiawei Han",
note = "This work was supported in part by the U.S. National Science Foundation grants IIS-0905215, U.S. Army Research Laboratory under Cooperative Agreement No. W911NF-09-2-0053 (NS-CTA). Chi Wang was supported by a Microsoft Research PhD Fellowship. Marina Danilevsky was supported by a National Science Foundation Graduate Re- search Fellowship grant NSF DGE 07-15088. The authors wish to acknowledge the University of Illinois at Urbana- Champaign Library (http://www.library.Illinois. edu), which provided support for this research. This work was supported in part by the U.S. National Science Foundation grants IIS–0905215, U.S. Army Research Laboratory under Cooperative Agreement No. W911NF– 09–2–0053 (NS-CTA). Chi Wang was supported by a Microsoft Research PhD Fellowship. Marina Danilevsky was supported by a National Science Foundation Graduate Research Fellowship grant NSF DGE 07-15088. The authors wish to acknowledge the University of Illinois at Urbana-Champaign Library (http://www.library.illinois. edu), which provided support for this research.; 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2013 ; Conference date: 11-08-2013 Through 14-08-2013",
year = "2013",
month = aug,
day = "11",
doi = "10.1145/2487575.2487631",
language = "English (US)",
series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",
pages = "437--445",
editor = "Rajesh Parekh and Jingrui He and Inderjit, {Dhillon S.} and Paul Bradley and Yehuda Koren and Rayid Ghani and Senator, {Ted E.} and Grossman, {Robert L.} and Ramasamy Uthurusamy",
booktitle = "KDD 2013 - 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
address = "United States",
}