Word Alignment of Biblical Hebrew Using inter alia Golign, a self-developed Android tablet tool
Typ
Examensarbete för masterexamen
Master Thesis
Master Thesis
Program
Datateknik 300 hp (civilingenjör)
Publicerad
2015
Författare
Klevbacke, Anders
Modellbyggare
Tidskriftstitel
ISSN
Volymtitel
Utgivare
Sammanfattning
The computer started being applied to biblical texts at least as far back as in the seventies, and in the middle of the eighties a database in the form of a digital text with an alignment of the Hebrew Old Testament and the Septuagint, the old Greek translation, was made available. Linguistic methods have also during many years have had impact on research in Biblical Hebrew. However, generic automatic word alignment methods have never been applied to Biblical Hebrew with Biblical Hebrew in focus. This thesis explores what opportunities word alignment might have to offer in this field. Experiments are made where the Biblical Hebrew text is converted into three different granularity levels and then aligned automatically to the two Swedish translations Svenska Folkbibeln 98 and Bibel 2000, for a total of six different alignment combinations. To assess the results, manual reference alignments, which allow calculation of evaluation metrics, are made. However, manual inspection of the voluminous output from the automatic aligner is also possible, and recommended. An important aspect of the thesis is how the processes around word alignment can provoke reflections around the Biblical Hebrew text and its relation to translations. The manual reference alignments are made using Golign, a self-developed tool for manual alignment and visualization of alignments. The tool has been tailor-made for working with Biblical Hebrew. However, at its core it is a general tool that could be used for other language combinations. Apart from the support for Biblical Hebrew, the most conspicuous features is that it is a touch sensitive Android tablet tool, and it allows for as many languages as the screen and the processor permit.
Beskrivning
Ämne/nyckelord
Data- och informationsvetenskap , Informations- och kommunikationsteknik , Computer and Information Science , Information & Communication Technology