Similarity based smoothing in language modeling

Szamonek Zoltán and Biró István: Similarity based smoothing in language modeling. In: Acta cybernetica, (18) 2. pp. 303-314. (2007)

[thumbnail of Szamonek_2007_ActaCybernetica.pdf]
Cikk, tanulmány, mű

Download (172kB) | Preview


In this paper, we improve our previously proposed Similarity Based Smoothing (SBS) algorithm. The idea of the SBS is to map words or part of sentences to an Euclidean space, and approximate the language model in that space. The bottleneck of the original algorithm was to train a regularized logistic regression model, which was incapable to deal with real world data. We replace the logistic regression by regularized maximum entropy estimation and a Gaussian mixture approach to model the language in the Euclidean space, showing other possibilities to use the main idea of SBS. We show that the regularized maximum entropy model is flexible enough to handle conditional probability density estimation, thus enable parallel computation tasks with significantly decreased iteration steps. The experimental results demonstrate the success of our method, we achieve 14% improvement on a reail world corpus.

Item Type: Article
Journal or Publication Title: Acta cybernetica
Date: 2007
Volume: 18
Number: 2
ISSN: 0324-721X
Page Range: pp. 303-314
Language: English
Place of Publication: Szeged
Event Title: Conference on Hungarian Computational Linguistics (4.) (2006) (Szeged)
Related URLs:
Uncontrolled Keywords: Számítástechnika, Nyelvészet - számítógép alkalmazása
Additional Information: Bibliogr.: 314. p. ; összefoglalás angol nyelven
Subjects: 01. Natural sciences
01. Natural sciences > 01.02. Computer and information sciences
06. Humanities
06. Humanities > 06.02. Languages and Literature
Date Deposited: 2016. Oct. 15. 12:25
Last Modified: 2022. Jun. 16. 14:03

Actions (login required)

View Item View Item