Two step CCA: A new spectral method for estimating vector models of words

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1551-1558

  Dhillon, Paramveer S ^a   Rodu, Jordan ^b   Foster, Dean P ^b   Ungar, Lyle H ^a  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

^b UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EIGEN DECOMPOSITION; HIGH DIMENSIONAL SPACES; LOW RANK; POS TAGGING; SAMPLE COMPLEXITY; SENTIMENT CLASSIFICATION; SINGLE-STEP; SPECTRAL METHODS; TWO-STEP PROCEDURE; UNLABELED DATA; VECTOR MODELS; WORD CO-OCCURRENCE;

LEARNING SYSTEMS;

SPECTROSCOPY;

EID: 84867133604     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (25)

1. Afonso, S., Bick, E., Haber, R., and Santos, D. Floresta sinta(c)tica: a treebank for Portuguese. In In Proc. LREC, pp. 1698-1703, 2002.
2. Ando, R. and Zhang, T. A framework for learning predictive structures from multiple tasks and unlabeled data. Journal of Machine Learning Research, 6:1817-1853, 2005.
3. Brown, P., deSouza, P., Mercer, R., Pietra, V. Della, and Lai, J. Class-based n-gram models of natural language. Comput. Linguist., 18:467-479, December 1992. ISSN 0891-2017.
4. Chang, Chih-Chung and Lin, Chih-Jen. "LIBSVM: a library for support vector machines", 2001. Software available at http://www.csie.ntu.edu.tw/ ~cjlin/libsvm.
5. Collobert, R. and Weston, J. A unified architecture for natural language processing: deep neural networks with multitask learning. ICML '08, pp. 160-167, New York, NY, USA, 2008. ACM.
6. Dhillon, Paramveer S., Foster, Dean, and Ungar, Lyle. Multi-view learning of word embeddings via cca. In Advances in Neural Information Processing Systems (NIPS), volume 24, 2011.
7. Dumais, S., Furnas, G., Landauer, T., Deerwester, S., and Harshman, R. Using latent semantic analysis to improve access to textual information. In SIGCHI Conference on human factors in computing systems, pp. 281-285. ACM, 1988.
8. Halko, Nathan, Martinsson, Per-Gunnar, and Tropp, Joel A. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Rev, 2011.
9. Hardoon, David and Shawe-Taylor, John. Sparse cca for bilingual word generation. In EURO Mini Conference, Continuous Optimization and KnowledgeBased Technologies, 2008.
10. Hotelling, H. Canonical correlation analysis (cca). Journal of Educational Psychology, 1935.
11. Hsu, D., Kakade, S., and Zhang, T. A spectral algorithm for learning hidden markov models. In COLT, 2009.
12. Kakade, S M. and Foster, Dean P. Multi-view regression via canonical correlation analysis. In Bshouty, Nader H. and Gentile, Claudio (eds.), COLT, volume 4539 of Lecture Notes in Computer Science, pp. 82-96. Springer, 2007.
13. Kromann, Matthias T. The danish dependency treebank and the underlying linguistic theory, in second workshop on treebanks and linguistic theories (tlt). In In Proc. LREC, pp. 217-220, 2003.
14. Lamar, Michael, Maron, Yariv, Johnson, Mark, and Bienenstock, Ehe. Svd and clustering for unsupervised pos tagging. ACL Short '10, pp. 215-219, Stroudsburg, PA, USA, 2010. Association for Computational Linguistics.
15. Marcus, Mitchell P., Marcinkiewicz, Mary Ann, and Santorini, Beatrice. Building a large annotated corpus of english: the penn treebank. Comput. Linguist., 19:313-330, June 1993. ISSN 0891-2017.
16. Merialdo, Bernard. Tagging english text with a probabilistic model. Comput. Linguist., 20, jun 1994.
17. Mnih, A. and Hinton, G. Three new graphical models for statistical language modelling. ICML '07, pp. 641-648, New York, NY, USA, 2007. ACM. ISBN 978-1-59593-793-3.
18. Pereira, F., Tishby, N., and Lee, L. Distributional clustering of English words. In 31st Annual Meeting of the ACL, pp. 183-190, 1993.
19. Seligman, Martin. Flourish: A Visionary New Understanding of Happiness and Well-being. Free Press, 2011.
20. Simov, K., Osenova, P., Slavcheva, M., Kolkovska, S., Balabanova, E., Doikoff, D., Ivanova, K., Simov, A., Simov, E., and Kouylekov, M. Building a linguistically interpreted corpus of bulgarian: the bultreebank. In In Proc. LREC, 2002.
21. Smith, Noah A. and Eisner, Jason. Contrastive estimation: training log-linear models on unlabeled data. ACL '05, pp. 354-362. Association for Computational Linguistics, 2005.
22. Suzuki, J. and Isozaki, H. Semi-supervised sequential labeling and segmentation using giga-word scale unlabeled data. In In ACL, 2008.
23. Teufel, Simone. The structure of scientific articles. CSLI Publications, 2010.
24. Turian, J., Ratinov, L., and Bengio, Y. Word representations: a simple and general method for semi-supervised learning. ACL '10, pp. 384-394, Stroudsburg, PA, USA, 2010. ACL.
25. Turney, P.D. and Pantel, P. From frequency to meaning: vector space models of semantics. Journal of Artificial Intelligence Research, 37:141-188, 2010.