A graph-based approach to named entity categorization in Wikipedia using conditional random fields
|A graph-based approach to named entity categorization in Wikipedia using conditional random fields|
|Author(s)||Watanabe Y., Asahara M., Matsumoto Y.|
|Published in||EMNLP-CoNLL 2007 - Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning|
|Keyword(s)||Unknown (Extra: Approximate inference, Baseline models, Computational costs, Conditional random field, Exact inference, Graph structures, Graph-based, Named entities, Reparameterization, Tree structures, Tree-based, Wikipedia, Conditional random fields (CRFs), Computational linguistics, Content based retrieval, HTML, Trees (mathematics), Forestry, Graphic methods, Random processes, Websites, Natural language processing systems)|
|Article||BASE, CiteSeerX, Google Scholar|
|Web||Ask, Bing, Google (PDF), Yahoo!|
|Download and mirrors|
|Local copy||Not available|
|Remote mirror(s)||Not available|
|Export and share|
|BibTeX, CSV, RDF, JSON|
|Browse properties · List of conference papers|
A graph-based approach to named entity categorization in Wikipedia using conditional random fields is a 2007 conference paper written in English by Watanabe Y., Asahara M., Matsumoto Y. and published in EMNLP-CoNLL 2007 - Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.
This paper presents a method for categorizing named entities in Wikipedia. In Wikipedia, an anchor text is glossed in a linked HTML text. We formalize named entity categorization as a task of categorizing anchor texts with linked HTML texts which glosses a named entity. Using this representation, we introduce a graph structure in which anchor texts are regarded as nodes. In order to incorporate HTML structure on the graph, three types of cliques are defined based on the HTML tree structure. We propose a method with Conditional Random Fields (CRFs) to categorize the nodes on the graph. Since the defined graph may include cycles, the exact inference of CRFs is computationally expensive. We introduce an approximate inference method using Treebased Reparameterization (TRP) to reduce computational cost. In experiments, our proposed model obtained significant improvements compare to baseline models that use Support Vector Machines.
- This section requires expansion. Please, help!
Probably, this publication is cited by others, but there are no articles available for them in WikiPapers. Cited 11 time(s)