A memory-based classification approach to marker-based EBMT

A memory-based classification approach to marker-based EBMT (2007)

by Antal Van Den Bosch

Venue:	Proceedings of the METIS-II Workshop on New Approaches to Machine Translation
Citations:	7 - 6 self

Datum	Value	Source
TITLE	A memory-based classification approach to marker-based EBMT	SVM HeaderParse 0.2
AUTHOR NAME	Antal Van Den Bosch	SVM HeaderParse 0.2
AUTHOR AFFIL	Dept. of Language and Information Sciences	SVM HeaderParse 0.2
AUTHOR ADDR	Tilburg University, P.O. Box 90153; NL-5000 LE Tilburg, The Netherlands	SVM HeaderParse 0.2
ABSTRACT	We describe a novel approach to examplebased machine translation that makes use of marker-based chunks, in which the decoder is a memory-based classifier. The classifier is trained to map trigrams of source-language chunks onto trigrams of target-language chunks; then, in a second decoding step, the predicted trigrams are rearranged according to their overlap. We present the first results of this method on a Dutch-to-English translation system using Europarl data. Sparseness of the class space causes the results to lag behind a baseline phrase-based SMT system. In a further comparison, we also apply the method to a word-aligned version of the same data, and report a smaller difference with a word-based SMT system. We explore the scaling abilities of the memory-based approach, and observe linear scaling behavior in training and classification speed and memory costs, and loglinear BLEU improvements in the amount of training examples. 1	SVM HeaderParse 0.2
YEAR	2007	INFERENCE
VENUE	Proceedings of the METIS-II Workshop on New Approaches to Machine Translation	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	63--72	INFERENCE
CITATIONS	30 found	ParsCit 1.0