@inproceedings{6906ab5aa46d42be90127ae216f7908c,
title = "Missed opportunities in translation memory matching",
abstract = "A translation memory system stores a data set of source-target pairs of translations. It attempts to respond to a query in the source language with a useful target text from the data set to assist a human translator. Such systems estimate the usefulness of a target text suggestion according to the similarity of its associated source text to the source text query. This study analyses two data sets in two language pairs each to find highly similar target texts, which would be useful mutual suggestions. We further investigate which of these useful suggestions can not be selected through source text similarity, and we do a thorough analysis of these cases to categorise and quantify them. This analysis provides insight into areas where the recall of translation memory systems can be improved. Specifically, source texts with an omission, and semantically very similar source texts are some of the more frequent cases with useful target text suggestions that are not selected with the baseline approach of simple edit distance between the source texts.",
keywords = "Edit distance, Text similarity, Translation memory",
author = "Friedel Wolff and Laurette Pretorius and Paul Buitelaar",
year = "2014",
language = "English",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "4401--4406",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
note = "9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
}