Algorithm for constructing six-dimensional tensor for the problem finding hidden semantic relations into the case of natural language texts

T.G. Voznyuk

Abstract


The paper presents an algorithm for constructing six-dimensional tensor containing statistical information on the syntactic structure of sentences. Conducting preliminary analysis of natural language texts aids was described. An example of Non-negaitve Tensor Factorization algorithm highlighting common semantic relations of sentences was given.

Prombles in programming 2014; 2-3: 273-278

References


Deerwester; Scott C. (Chicago, IL), Dumais; Susan T. (Berkeley Heights, NJ), Furnas; George W. (Madison, NJ), Harshman; Richard A. (London, CA), Landauer; Thomas K. (Summit, NJ), Lochbaum; Karen E. (Chatham, NJ), Streeter; Lynn A. (Summit, NJ). Computer information retrieval using latent semantic structure, 1988.

Thomas Hofmann. Probabilistic Latent Semantic Indexing // Proceedings of the Twenty-Second Annual International SIGIR Conference on Research and Development in Information Retrieval (SIGIR-99), 1999.

Max Welling and Markus Weber. Positive Tensor Factorization // Pattern Recognition Letters. – 2001. –22 (12), P. 1255–1261.

TIM VAN DE CRUYS. A non-negative tensor factorization model for selectional preference induction // Natural Language Engineering. –2010. – 16 (4): 417–437.

Марченко О.О. Застосування методів невід’ємної факторизації тензорів для визначення стійких семантичних відношень при обробці великих текстових корпусів // Вісник Київського університету: Серія: фізико-математичні науки. – 2012. – № 4.

Daniel Cer, Marie-Catherine de Marneffe, Daniel Jurafsky, and Christopher D. Manning. Parsing to Stanford Dependencies: Trade-offs between speed and accuracy. 2010.

Marie-Catherine de Marnee and Christopher D. Manning. Stanford typed dependencies manual, 2008.

Max Welling and Markus Weber. Positive Tensor Factorization. Pattern Recognition Letters, 2001.


Refbacks

  • There are currently no refbacks.