An Automated Language Translation System for Classical Music Titles
M.J.C. Dingjan (TU Delft - Electrical Engineering, Mathematics and Computer Science)
R.W. Kapel (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Maarten P. Sijm (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Casper Karreman – Mentor
CCS Liem – Coach
Ingmar Vroomen – Graduation committee member
Otto W. Visser – Graduation committee member
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Muziekweb is the biggest source of music that has been released in the Netherlands. At this moment, all of their data is currently in Dutch. However, Muziekweb wishes their classical music titles to be translated to other languages as well. Since over 250.000 classical music titles exist, it is too much work to be done manually. Therefore, Muziekweb requested a program which can automatically translate titles. With these translations, not only can they deliver their data to more people, it will be easier in the future to link their data to other international sources.
Research has been done on these titles on how they are structured. This knowledge is required to split up these titles in smaller parts. Some of these parts can only have a limited set of Dutch words in them. Therefore, these translations can be translated using a lookup table. Besides these parts, some parts cannot be as easily translated, since they have a cultural history behind them. Therefore, these parts need to be translated differently. To do this, a connection is set up with external databases to find translations for these parts. To be able to improve this program in the future, the program is extensible as well, either for translating to more languages or linking up with more databases.