center for research in urdu language processing pan localization project a regional initiative to...

29
Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ل گ اء ن ث ز ک ر م ات ق ی ق ح ت اردو ان ن س ک ا پ، ۲۰۰۵ SANA GUL Center for Research in Urdu Language Processing Pakistan, 2005

Upload: elizabeth-glenn

Post on 18-Dec-2015

218 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

PAN Localization ProjectA Regional Initiative to Develop Local Language

Computing Capacity in Asia

ثناء گل اردو تحقیقاتمرکز

۲۰۰۵ ، پاکستانSANA GULCenter for Research in Urdu Language Processing

Pakistan, 2005

Page 2: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Introduction to Center for Research in Urdu Language Processing

Introduction to PAN Localization Project

Scope of Localization & Introduction to this Training

Presentation Highlights

Page 3: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Page 4: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP ObjectivesCRULP Objectives

► To conduct To conduct linguistic researchlinguistic research for Urdu and regional for Urdu and regional

languageslanguages

► To participate in To participate in standardization effortsstandardization efforts in Urdu and in Urdu and

regional languagesregional languages

► To evolve To evolve computational modelscomputational models of Urdu and regional of Urdu and regional

languageslanguages

► Promote Promote content developmentcontent development in Urdu and regional in Urdu and regional

languageslanguages

Page 5: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP ResearchCRULP Research

► LinguisticsLinguistics

► Script ProcessingScript Processing

► Language ProcessingLanguage Processing

► Speech ProcessingSpeech Processing

Page 6: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP ResourcesCRULP Resources

►TeamTeam 4 Full-time Faculty Members4 Full-time Faculty Members Adjunct FacultyAdjunct Faculty 12 Graduate Students12 Graduate Students 45 Undergraduate Students45 Undergraduate Students 25 Full-time staff25 Full-time staff

Page 7: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP CourseworkCRULP Coursework

► Phonetics and PhonologyPhonetics and Phonology► Morphology and SyntaxMorphology and Syntax

► Digital Signal Processing Digital Signal Processing ► Random Variables and Stochastic Processes Random Variables and Stochastic Processes ► Speech ProcessingSpeech Processing

► Computational LinguisticsComputational Linguistics

► Image ProcessingImage Processing► Calligraphy and Font DevelopmentCalligraphy and Font Development

Page 8: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP Research - LinguisticsCRULP Research - Linguistics

►AreasAreas Acoustic Phonetics Acoustic Phonetics PhonologyPhonology MorphologyMorphology SyntaxSyntax

Page 9: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP Research - ScriptCRULP Research - Script

► Font Development: Nafees Font FamilyFont Development: Nafees Font Family Nafees Nasta’leeq, Nafees Naskh, Nafees Pakistani Nafees Nasta’leeq, Nafees Naskh, Nafees Pakistani

Naskh (Urdu, Punjabi, Pashto, Sindhi, Balochi, Siraiki)Naskh (Urdu, Punjabi, Pashto, Sindhi, Balochi, Siraiki) Freely downloadable from Freely downloadable from www.crulp.orgwww.crulp.org Supported mainly by UNDP/IDRC/APNIC Small Grants Supported mainly by UNDP/IDRC/APNIC Small Grants

Program and partially by Microsoft, PakistanProgram and partially by Microsoft, Pakistan

►Optical Character RecognitionOptical Character Recognition Naskh (segmentation based)Naskh (segmentation based) Nasta’leeq (Ligature based)Nasta’leeq (Ligature based)

Page 10: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Page 11: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Nasta’leeNasta’lee

qq

KufiKufi

SulusSulus

DiwaniDiwani

RiqaRiqa

NaskhNaskh

القمر ومسالش سخرو

Page 12: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP Research - LanguageCRULP Research - Language

►Corpus DevelopmentCorpus Development►Computational Linguistic ApplicationsComputational Linguistic Applications

Spell CheckerSpell Checker Grammar CheckerGrammar Checker LexiconLexicon English to Urdu Machine TranslationEnglish to Urdu Machine Translation

Page 13: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

CRULP Research - SpeechCRULP Research - Speech

►Text to Speech SynthesisText to Speech Synthesis►Automatic Speech RecognitionAutomatic Speech Recognition

Page 14: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

ProjectsProjects

►Nafees Font FamilyNafees Font Family►Urdu Localization ProjectUrdu Localization Project►Microsoft Spell CheckerMicrosoft Spell Checker►PAN LocalizationPAN Localization

Page 15: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

PAN Localization Project

www.panl10n.net

Page 16: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

PAN Localization Project

Partnership PAN program of IDRC CRULP at NUCES

Objectives Develop localization technology for Asian

languages Develop human resource to develop and use

localized computing Research into policy framework to develop

local language computing Timelines

January 2004 till December 2006

Page 17: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

PAN L10n Project Collaborations

1. BRAC University, Bangladesh2. Department of IT, Ministry of Information and

Communications, Bhutan3. Khmer Computerization Committee, National ICT

Development Agency, Cambodia4. Science Technology and Environment Agency, Laos5. Madan Puraskar Pustakalaya & Tribhuvan

University Nepal6. University of Colombo School of Computing, Sri

Lanka7. …

Page 18: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Salient PAN L10n Project Outputs

Localization Technology Asian Localization Peer Support

Network Bibliography of Asian Localization Who’s Who of Asian Localization Multi-lingual Website:

www.PANL10n.net Asian Localization Handbook

Page 19: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Country-wise Project Outputs

Page 20: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Scope of Localization

Page 21: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Localization

“enabling computing experience according to linguistic culture of the user”

Page 22: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Localization Requirements

Standards Basic Applications Intermediate Applications Advanced Applications Soft Issues

Page 23: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Standards

Character Set Keyboard/Keypad layout Locale Collation Sequence Terminology Translation Fonts (?) …

Page 24: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Basic Applications

Character set encoding(s) Utility for converting among

various encodings Keyboard/Keypad drivers Collation algorithm Local language interface Fonts for various devices …

Page 25: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Intermediate Applications

Find/Replace utility Natural language

processor/Bidirectional processor Lexicon Spell checker …

Page 26: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Advanced Applications

Grammar checker Automatic speech recognition Text to speech system Automatic machine translation Optical character recognition Handwriting recognition Speech to speech translation …

Page 27: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Introduction to Training

Objectives Overview scope of localization Study in detail basic issues regarding

localization standards and development

Develop Asian peer support network

Page 28: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

Summary of Topics

Encoding Standards Font Development Localization on Microsoft Platform Localization on Linux Platform Defining Normalization and

Collation Overview Advanced Applications Overview Software Engineering

Page 29: Center for Research in Urdu Language Processing PAN Localization Project A Regional Initiative to Develop Local Language Computing Capacity in Asia ثناء

Center for Research in Urdu Language Processing

ہی شکر

SANA [email protected]

Regional Research OfficerPAN Localization project

(www.panl10n.net)