The effects of word order and segmentation on translation retrieval performance

Authors:
Timothy Baldwin;Hozumi Tanaka
Affiliations:
Tokyo Institute of Technology, Tokyo, Japan;Tokyo Institute of Technology, Tokyo, Japan
Venue:
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Year:
2000

Citing 7
Cited 6

A comparison of indexing techniques for Japanese text retrieval

SIGIR '93 Proceedings of the 16th annual international ACM SIGIR conference on Research and development in information retrieval
Foundations of statistical natural language processing

Foundations of statistical natural language processing
The String-to-String Correction Problem

Journal of the ACM (JACM)
Example retrieval from a translation memory

Natural Language Engineering
A new method of N-gram statistics for large number of n and automatic extraction of words and phrases from large text data of Japanese

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
CTM: an example-based translation aid system

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 4
The SMART Retrieval System—Experiments in Automatic Document Processing

The SMART Retrieval System—Experiments in Automatic Document Processing

Improvement of a Whole Sentence Maximum Entropy Language Model using grammatical features

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Low-cost, high-performance translation retrieval: dumber is better

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
EXTRA: a system for example-based translation assistance

Machine Translation
An efficient pattern matching algorithm for comparative Genome sequence analysis

ACC'08 Proceedings of the WSEAS International Conference on Applied Computing Conference
Comparative genome sequence analysis by efficient pattern matching technique

WSEAS Transactions on Information Science and Applications
Hozumi tanaka

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This research looks at the effects of word order and segmentation on translation retrieval performance for an experimental Japanese-English translation memory system. We implement a number of both bag-of-words and word order-sensitive similarity metrics, and test each over character-based and word-based indexing. The translation retrieval performance of each system configuration is evaluated empirically through the notion of word edit distance between translation candidate outputs and the model translation. Our results indicate that character-based indexing is consistently superior to word-based indexing, suggesting that segmentation is an unnecessary luxury in the given domain. Word order-sensitive approaches are demonstrated to generally outperform bag-of-words methods, with source language segment-level edit distance proving the most effective similarity metric.