Cache-based Statistical Language Models of English and Highly Inflected Lithuanian

Cache-based Statistical Language Models of English and Highly Inflected Lithuanian (2005)

Cached

Download Links

[donelaitis.vdu.lt]

by Airenas Vaičiūnas , Gailius Raškinis

Versions

Version 0

Version History

Metadata Version 0

Datum	Value	Source
TITLE	Cache-based Statistical Language Models of English and Highly Inflected Lithuanian	SVM HeaderParse 0.2
AUTHOR NAME	Airenas Vaičiūnas	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Applied Informatics, Vytautas Magnus University	SVM HeaderParse 0.2
AUTHOR ADDR	Vileikos 8, LT-44404 Kaunas, Lithuania	SVM HeaderParse 0.2
AUTHOR NAME	Gailius Raškinis	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Applied Informatics, Vytautas Magnus University	SVM HeaderParse 0.2
AUTHOR ADDR	Vileikos 8, LT-44404 Kaunas, Lithuania	SVM HeaderParse 0.2
ABSTRACT	Abstract. This paper investigates a variety of statistical cache-based language models built upon three corpora: English, Lithuanian, and Lithuanian base forms. The impact of the cache size, type of the decay function, including custom corpus derived functions, and interpolation technique (static vs. dynamic) on the perplexity of a language model is studied. The best results are achieved by models consisting of 3 components: standard 3-gram, decaying cache 1-gram and decaying cache 2-gram that are joined together by means of linear interpolation using the technique of dynamic weight update. Such a model led up to 36 % and 43 % perplexity improvement with respect to the 3-gram baseline for Lithuanian words and Lithuanian word base forms respectively. The best language model of English led up to a 16 % perplexity improvement. This suggests that cache-based modeling is of greater utility for the free word order highly inflected languages.	SVM HeaderParse 0.2
YEAR	2005	SVM HeaderParse 0.2
CITATIONS	23 found	ParsCit 1.0