Development of a Semantic and Syntactic Model of Natural Language by Means of Non-negative Matrix and Tensor Factorization

Text, Speech and Dialogue - Lecture Notes in Computer Science ◽

10.1007/978-3-319-10816-2_40 ◽

2014 ◽

pp. 324-335

Author(s):

Anatoly Anisimov ◽

Oleksandr Marchenko ◽

Volodymyr Taranukha ◽

Taras Vozniuk

Keyword(s):

Natural Language ◽

Tensor Factorization

Download Full-text

Semantic and Syntactic Model of Natural Language Based on Tensor Factorization

Natural Language Processing and Information Systems - Lecture Notes in Computer Science ◽

10.1007/978-3-319-07983-7_7 ◽

2014 ◽

pp. 51-54

Author(s):

Anatoly Anisimov ◽

Oleksandr Marchenko ◽

Volodymyr Taranukha ◽

Taras Vozniuk

Keyword(s):

Natural Language ◽

Tensor Factorization

Download Full-text

A non-negative tensor factorization model for selectional preference induction

Natural Language Engineering ◽

10.1017/s1351324910000148 ◽

2010 ◽

Vol 16 (4) ◽

pp. 417-437 ◽

Cited By ~ 17

Author(s):

TIM VAN DE CRUYS

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Semantic Similarity ◽

Language Processing ◽

Tensor Factorization ◽

Promising Tool ◽

Occurrence Data ◽

Factorization Model ◽

Distributional Similarity ◽

Factorization Methods

AbstractThe distributional similarity methods have proven to be a valuable tool for the induction of semantic similarity. Until now, most algorithms use two-way co-occurrence data to compute the meaning of words. Co-occurrence frequencies, however, need not be pairwise. One can easily imagine situations where it is desirable to investigate co-occurrence frequencies of three modes and beyond. This paper will investigate tensor factorization methods to build a model of three-way co-occurrences. The approach is applied to the problem of selectional preference induction, and automatically evaluated in a pseudo-disambiguation task. The results show that tensor factorization, and non-negative tensor factorization in particular, is a promising tool for Natural Language Processing (nlp).

Download Full-text