Word sense disambiguation using label propagation based semi-supervised learning
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Relation extraction using label propagation based semi-supervised learning
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Global learning of noun phrase anaphoricity in coreference resolution via label propagation
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
On the difficulty of clustering microblog texts for online reputation management
WASSA '11 Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis
Discovering filter keywords for company name disambiguation in twitter
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
With the rapid growth of user generated media, Twitter has become an important information resource where users share fresh information on any subject. Pursuing on the problem of finding related tweets to a given organization, we propose two stages based organization name disambiguity. Insufficient information and the diversity of organizations are two key problems for this task. We induce multiple types of features to enrich the information of organization to solve the problem of insufficient information. The relationships between tweets and organization, the relationships among tweets are mined in two stages to solve the diversity of organization. Furthermore, we probe the distribution of organization names' ambiguity and its influence to different classifiers. Our experimental results on WePS-3 prove the proposed methods are effective and promising in performing this task.