Domain-Assisted Product Aspect Hierarchy Generation: Towards Hierarchical Organization of Unstructured Consumer Reviews

From Cohen Courses
Revision as of 15:44, 29 September 2012 by Ydalal (talk | contribs) (→‎Summary)
Jump to navigationJump to search

Citation

 author    = {Jianxing Yu, Zheng-Jun Zha, Meng Wang, Kai Wang, Tat-Seng Chua},
 title     = {Domain-Assisted Product Aspect Hierarchy Generation: Towards Hierarchical Organization of Unstructured Consumer Reviews},
 booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing},
 month     = {July},
 year      = {2011},
 pages     = {140--150},

Online version

ACLWEB 2011

Summary

This paper propose to hierarchically organize consumer reviews according to an aspect hierarchy, so as to transfer the reviews into a useful knowledge structure. This paper develops a domain-assisted approach to generate an aspect hierarchy by integrating domain knowledge and consumer reviews. They use external hierarchies such as Wordnet and Open Directory Project to learn semantic distance between aspects. They use aspect hierarchy to identify implicit aspects.

Background

Methodology

Study Plan