Marina Danshina - The methodology of automated decryption of znamenny chants
-
Upload
aist -
Category
Data & Analytics
-
view
104 -
download
1
Transcript of Marina Danshina - The methodology of automated decryption of znamenny chants
THE METHODOLOGY OF AUTOMATED DECODING OF
ZNAMENNY CHANTS
Marina Danshina, Andrew Philippovich, Irina Golubeva
8 April, 2016, AIST
Automated component methodology
We created an automated system - "Computer Semiography".
The system consists of 5 main modules:
1) A module of the chants' input into the database,
2) Review of the manuscripts in electronic form,
3) Formation of a linguistic model of ancient musical chants, translation models,
4) Decoding of the chants.
5) Music editor module
Linear and Znamenny notations in our system
● Describing the pitch and duration of notes
● A lot of tips for translating from special ancient books - alphabets and dvoyeznamenniks
● Modules in system could be used separately
General scheme of the technique
1. Selection of basic data. Decoding of chants can be made depending on the chosen chants.
2. Transfer of manuscripts into electronic form. Scanning and input of chants, processing and preservation of the information in the databases.
3. Development and setting up of the translated dictionary. Choice of structuring methods and sources for creation of decoding rules; carrying out necessary researches.
4. Transformation (decoding) of the manuscript by means of the dictionary.
5. Preparation of the manuscript, materials and results of research for electronic representation and playing in the web environment.
General scheme of the technique
Development and setting up of the translated dictionary
● Creation of the dictionary on the basis of popevkas (productive model),
● Creation of the dictionary on the basis of a dvoznamennik (n-gram model),
● Combined method.
Formation of the dictionary based on popevka
Formation of the dictionary based on a dvoznamennik
Fragment of n-gram model.
Combined dictionary
1) As a preliminary stage, experts set rules from the first method in the first place and then they set rules recived from statistical machine translation.
2) Then experts can carry out the analysis of all rules. Editing of probability or a priority of the rule.
Decoding of the manuscript by means of the dictionary
Conclusion
1. The developed set of services is intended to simplify the most time-consuming operations, which researchers-medievalists face. As a result, researchers spend less time on checking and calculating any data.
2. The offered decoding methodology of the Znamenny Chants allows producing three main components required for the Znamenny Chants decoding a dictionary with the transfer rules from znams to notes, a version of the translated manuscript into the linear notation, language model and model of Znamenny Chants translation. Transfer of chants into electronic format makes them more available.
3. This work has developed software, which allows inputting Znamenny Chants into the database, edit them, and look through them. We have realized the language construction and translation modules that allow transferring Znamenny Chants into a linear notation. The program is also able to build dvoeznamenny frequency dictionaries and indexes of znams.
Пример перевода
Этапы перевода:1.Составление триграмм2.Поиск триграммы в модели перевода3.Поиск нот (перевода) в языковой модели4.Вычисление итоговой вероятности5.Выбор лучшего правила6.Сохранение итогового перевода
P1 – вероятность триграммы переводаP2 – вероятность переводаP3 – итоговая вероятность перевода