Abstract：This paper proposes a new method called Multi-redundant-labeled CRFs and applies it on sentence sentiment analysis. This method can not only solve ordinal regression problems effectively, but also obtain global optimal result over multiple cascaded subtasks by merging subjective/objective classification, polarity classification and sentimental strength rating into an integrated model, with each subtask maintaining its own feature types. Experiments on sentiment classification of sentences show a better performance than standard CRFs, and thus validate the effectiveness of this method. Additionally, this method theoretically provides a way to solve ordinal regression problems for the algorithms whose training is based on maximization likelihood estimation.
[1] Bo Pang, Lillian Lee. 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts[A]. In: Proceedings of the ACL 2004[C]. 2004. 271-278.[2] Bo Pang and Lillian Lee. 2005. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales[A]. In: Proceedings ofthe ACL 2005[C]. 115. [3] Y. Mao, G. Lebanon, 2007. Isotonic Conditional Random Fields and Local Sentiment Flow[A]. In: The Neural Information Processing Systems (NIPS19)[C]. 2007. [4] Theresa Wilson, Paul Hoffmann, Swapna Somasundaran, et al. OpinionFinder: A system for subjectivity analysis[A]. Demo in Human Language Technologies Conference/Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005)[C]. Vancouver, Canada: 2004. [5] R. Herbrich, T. Graepel, and K. Obermayer. Large margin rank boundaries for ordinal regression[M]. In: Advances in Large Margin Classifiers. chapter 7, MIT Press, 2000. 115-132. [6] W. Chu and S. S. Keerthi. New approaches to support vector ordinal regression[A]. In: International Conference on Machine Learning (ICML-05)[C]. 145-152. [7] Ling Li Hsuan-Tien Lin Ordinal Regression by Extended Binary Classification[A]. In: The Neural Information Processing Systems (NIPS19)[C]. 2007. [8] J Lafferty, A McCallum, F Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data[A]. In: The Proceedings of International Conference on Machine Learning (ICML)[C]. 2001, 282-289. [9] Fei Sha and Fernando Pereira, 2003 Shallow Parsing with Conditional Random Fields[A]. In: The proceedings of Human Language Technology/North American chapter of the Association for Computational Linguistics annual meeting (HLT/NAACL)[C]. 2003. [10] Wei Chu ,Zoubin Ghahraman Gaussian Processes for Ordinal Regression[J]. The Journal of Machine Learning Research Volume 6, (December 2005) 1019-1041.
2007, Vol. 21 
