An Approach to Ancient-to- modern and Cross-script Information Access for Traditional Mongolian Historical Collections

poster / demo / art installation
Authorship
  1. 1. Biligsaikhan Batjargal

    School of Science and Engineering - Ritsumeikan University

  2. 2. Garmaabazar Khaltarkhuu

    Mongolia-Japan Center for Human Resources Development - National University of Mongolia

  3. 3. Fuminori Kimura

    College of Information Science and Engineering - Ritsumeikan University

  4. 4. Akira Maeda

    College of Information Science and Engineering - Ritsumeikan University

Work text
This plain text was ingested for the purpose of full-text search, not to preserve original formatting or readability. For the most complete copy, refer to the original conference program.


1
An Approach to Ancient-to-
modern and Cross-script
Information Access for
Traditional Mongolian
Historical Collections
Batjargal, Biligsaikhan
biligsaikhan@gmail.com
Graduate School of Science and Engineering,
Ritsumeikan University, Japan
Khaltarkhuu, Garmaabazar
garmaabazar@gmail.com
Mongolia-Japan Center for Human Resources
Development, Mongolia
Kimura, Fuminori
fkimura@is.ritsumei.ac.jp
College of Information Science and
Engineering, Ritsumeikan University, Japan
Maeda, Akira
amaeda@is.ritsumei.ac.jp
College of Information Science and
Engineering, Ritsumeikan University, Japan
The main purpose of this research is to develop
a system to keep over 800-year-old historical
records written in traditional Mongolian script
for future use, to digitize all existing records and
to make those valuable data available for public
viewing and screening. There are over 50,000
registered manuscripts and historical records
written in traditional Mongolian script stored in
the National Library of Mongolia. About 21,100
of them are handwritten documents. There
are many more manuscripts and books stored
in libraries of other countries such as China,
Russia and Germany. Despite the importance
of keeping 800-year-old historical materials in
good condition, the Mongolian environment
for material storage is not satisfactory to keep
historical records for a long period of time
(Tungalag, 2005). We believe that the most
efficient and effective way to keep and protect
old materials of historical importance while
making them publicly available is to digitize
historical records and create a digital library.
Mongolia introduced a new writing system
(Cyrillic) in 1941. This was a radical change
and alienated the traditional Mongolian script.
The spelling of words and suffixes in traditional
Mongolian script differs from spellings in
modern Mongolian (Cyrillic). This is due to
traditional Mongolian script preserving a more
ancient language while modern Mongolian
reflects pronunciation differences in modern
dialects. Spellings used in traditional Mongolian
script reflect the Mongolian language spoken
in the days of Genghis Khan but also contain
elements of the ancient Mongolian language
spoken before that era. Thus traditional
Mongolian has a different grammar and
a distinct dialect from modern Mongolian.
At present, people use dictionaries with
transcribing suffixes to overcome differences.
Recently ancient historical documents in
traditional Mongolian script are being digitized
and made publicly available, thanks to advances
in innovative information technologies, and the
popularity of the Internet. In Windows Vista,
and later versions, especially in Windows 7, text-
display support for traditional Mongolian script
and the input locale is enabled. The Uniscribe
driver was updated to support OpenType
advanced typographic functionality of complex
text layouts such as traditional Mongolian
script. Traditional Mongolian script is written
vertically from top to bottom in columns
advancing from left to right.
However, retrieval of the required information
in modern Mongolian from traditional
Mongolian script documents is not a simple
task, due to substantial changes in Mongolian
language over time. We want to offer an
information retrieval method that considers
language difference over time. Our goal in this
research is to develop a retrieval system where
a user can access cross-period and cross-script
databases with a query input in a modern
language.
1. Related Research
Much research has been conducted in the last
decade on Cross-language information retrieval
(CLIR) – a technique to retrieve documents
in one language through a query in another
language. On the contrary, little research has
been completed regarding information retrieval
techniques for historical documents. Still less,
almost none of the breakthroughs in research

2
on information retrieval and information access
have aimed at retrieving information in
the native language from an ancient, cross-
period and/or cross-script foreign language
documents. Almost none of the CLIR systems
has integrated either modern (Cyrillic) or
traditional (ancient) Mongolian language due to
its research backwardness.
Few approaches (Ernst-Gerlach et al., 2007;
Garmaabazar et al., 2008; Kimura et al.,
2009) that could be considered a cross-period
information retrieval have been proposed.
Little research has been completed regarding
information retrieval techniques for historical
documents. Ernst-Gerlach et al. (2007)
developed a retrieval method that considers the
spelling differences and variations over time.
They focused on modern and archaic German.
Kimura et al. (2009) proposed a retrieval
method that considers not only language
differences over time, but also cultural and age
differences in the same language. They focused
on retrieval techniques for modern and archaic
Japanese. Khaltarkhuu et al. (2008) proposed a
retrieval technique that considers cross-period
differences in dialect, script and writing systems
of the same language. They focused on modern
and traditional Mongolian.
2. System Architecture
We propose a simple model to cope with cross-
period and cross-script queries. The proposed
model is shown in Figure 1.
Figure 1
In the first stage, the query in a modern language
will be translated into a query in an ancient form.
Consequently, a query in the ancient language
is submitted as a retrieval query for digital
collections. The proposed model is expected to
perform cross-period information retrieval and
a user will be able to access ancient historical
databases with a query input in a modern
language. We will adopt a dictionary-based
query translation approach.
3. Implementation of the
Proposed System
Although it is not easy to develop such a retrieval
system, we will utilize existing approaches
(Garmaabazar et al., 2008; Kimura et al.,
2009) to realize the proposed approach. A
prototype called the Traditional Mongolian
Script Digital Library
1
(TMSDL) (Garmaabazar
et al., 2008), which could be considered a cross-
period information retrieval system, has been
developed. The retrieval method of the TMSDL
considers cross-period differences in writing
system of the ancient and modern Mongolian
languages.
However, retrieval techniques of the TMSDL
have not considered irregular words which
have different meanings but are written and
pronounced exactly the same in modern
Mongolian and have different forms in
traditional Mongolian. Also, word sense
disambiguation has not been considered. Thus,
we enhanced the TMSDL by integrating
a dictionary-based cross-period information
retrieval approach. We utilized the developing
online version of the Tsevel's concise Mongolian
dictionary
2
(Tsevel, 1966) under the Creative
Commons Attribution-Noncommercial-Share
Alike 3.0 Unported license.
The Altan Tobchi (year 1604, 164pp) –
A chronological book of ancient Mongolian
Kings, Genghis Khan and the Mongol Empire
(the largest contiguous empire in history) is
shown in Figure 2, with modern Mongolian
input interface in the new version of TMSDL
(TMSDLv2). A database of such historical
records in the TMSDLv2 with English or modern
Mongolian query input will help someone
conducting research in the history of the High
Middle Ages, accessing materials written in
an ancient language (traditional Mongolian) in
order to understand 13
th
-14
th
century history of
Asia.

If this content appears in violation of your intellectual property rights, or you see errors or omissions, please reach out to Scott B. Weingart to discuss removing or amending the materials.

Conference Info

Complete

ADHO - 2010
"Cultural expression, old and new"

Hosted at King's College London

London, England, United Kingdom

July 7, 2010 - July 10, 2010

142 works by 295 authors indexed

XML available from https://github.com/elliewix/DHAnalysis (still needs to be added)

Conference website: http://dh2010.cch.kcl.ac.uk/

Series: ADHO (5)

Organizers: ADHO

Tags
  • Keywords: None
  • Language: English
  • Topics: None