MDL-Based Models for Transliteration Generation . . . . . . 1 - PowerPoint PPT Presentation

. University of Helsinki July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) July 30, 2013 SLSP 2013 Department of Computer Science Javad Nouri, Lidia Pivovarova, and Roman Yangarber . MDL-Based Models for Transliteration Generation . . . . . . 1 / 27

. . Etymon Project Models Prediction Pre-processing Evaluation Baselines . 4 Review Results . . 5 Future Work J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 Motivation Methods . Introduction . . . . Outline . . 1 Transliteration 3 Applications Challenges . 2 Data Data-sets . . 2 / 27

Таррагона Таррагон ﺎﻧﻮﮔارﺎﺗ הנוגרט Тарраґона ةنوغارط ट ै र ा ग ो न ा タラゴナ塔拉戈纳 타라고나 ታ ራ ጎ ና த ா ர ா க ோணம ் July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) . . Taragona Tarragona or pronunciation Predicting word representation in another language, based on spelling Transliteration . . . . 3 / 27

. Tarragona July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) . Taragona 3 / 27 or pronunciation . Transliteration . . . Predicting word representation in another language, based on spelling Таррагона Таррагон æ ﺎﻧﻮﮔارﺎﺗ הנוגרט Тарраґона ةنوغارط ट ै र ा ग ो न ा タラゴナ塔拉戈纳 타라고나 ታ ራ ጎ ና த ா ர ா க ோணம ்

. . . . . . Where can it be used? Machine Translation: proper names, terms Information Retrieval, Information Extraction, Named Entity Recognition Several scripts for a language J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 4 / 27

. . . . . . Challenges J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 5 / 27

. . . . . . Challenges Transliteration can be based on: pronunciation spelling translation J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 5 / 27

. . . . . . Challenges Transliteration can be based on: pronunciation spelling translation J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 5 / 27 Санкт-Петербург /Sankt-Peterburg/

. . July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) Pietari Saint Petersburg translation spelling pronunciation Transliteration can be based on: Challenges . . . . 5 / 27 Санкт-Петербург /Sankt-Peterburg/

. . . . . . Challenges Transliteration can be based on: pronunciation spelling translation Different transliterations for the same name J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 5 / 27

. . . . . . Leo Tolstoy Lev Tolstoy J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 5 / 27 Лев Толстой

. Alphabetic July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) ... Katakana, ... Syllabic Arabic, Persian, Hebrew, ... Consonantal English, Russian, ... Scripts are based on different principles: . Different transliterations for the same name translation spelling pronunciation Transliteration can be based on: Challenges . . . . 5 / 27

. . . . . . Data J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 7 / 27

. . . . . . Data Titles devoted to the same entities in different languages are transliterations of each other. Language links can be used to find such pairs. Use categories to distinguish different types of data (locations, people, etc.) J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 7 / 27

. En–Fa 317 Ru–Jp 407 En–Gr 828 Ru–Fr 840 870 Ru–En Ru–Fa 1245 En–He 1136 Ru–En Russian Cities 1471 Russian Writes 1462 American Actors Fa–Ru July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) Locations are more homogeneous than person names. Russian writers contains mainly Russian names, etc. Using Wikipedia categories increases homogeneity in data 469 1893 French Cities Fa–Ru Iranian Locations 439 Fa–En Iranian Cities 828 Fr–Ru En–Ru of pairs . 1 French 3 Consonantal Farsi 2 Alphabetic English Script Type 4 Language # Data-sets . . . . Alphabetic Greek pair Data-set of pairs pair Size: # Language Data-set Size: # Language Alphabetic Alphabetic Russian 7 Syllabic Japanese (Katakana) 6 Consonantal Hebrew 5 8 / 27

. . . Combined . Phonetics-based . Spelling-based Spelling-based . . Hybrid . Extraction J. Nouri, L. Pivovarova, R. Yangarber (UH) SLSP 2013 July 30, 2013 MDL MDL . . . . . . Methods Karimi, S., Scholer, F., Turpin, A.: Machine transliteration survey. ACM Computing Surveys 43(3) (2011) . . Transliteration . Generation . Rule-based . Noisy Channel 10 / 27

MDL-Based Models for Transliteration Generation . . . . . . 1 - PowerPoint PPT Presentation

. University of Helsinki July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) July 30, 2013 SLSP 2013 Department of Computer Science Javad Nouri, Lidia Pivovarova, and Roman Yangarber . MDL-Based Models for Transliteration

A Python Toolkit for Universal Transliteration . . . . . Ting Qian 1 , Kristy Hollingshead 2 ,

A Log-linear Block Transliteration Model based on Bi-Stream HMMs Bing Zhao Joint work with

Other models used to Model Demand Dr. Randa Oqab Mujalli TRIP GENERATION Dr. Randa Oqab Mujalli

ICTs in education Moving from 1 Generation to 2 Generation models a framework for program

Implicit Generation and Generalization with Energy Based Models Yilun Du and Igor Mordatch

Understorey identification through the generation of canopy base height models based on LiDAR

Cross-Language IR at University of Tsukuba Automatic Transliteration for Japanese, English, and

Distributed Generation of Random Graphs Based on Social Network Models Kyrylo Institute for

Transcription, transliteration, transduction, and translation A typology of crosslinguistic name

Automatic Code Generation from Stateflow Models Andres Toom IB Krates O / Institute of

Using Accessor Variety Features of Source Graphemes in Machine Transliteration of English to

Recurrent Neural Models: Language Models, and Sequence Prediction and Generation CMSC 473/673

LIGA and Syllabification Approach for Language Identification and Back Transliteration : Shared

Encoding transliteration variation through dimensionality reduction Parth Gupta 1 , Paolo Rosso 1

Translation & Transliteration between Related Languages Anoop Kunchukuttan Mitesh Khapra

Code Generation Issues Aslan Askarov aslan@cs.au.dk Based on slides by E. Ernst

Model-Based Testing: Automated Generation of Test Cases, Test Data, and Test Procedures from

Agent-Based Modeling and Simulation Models, Agent-based Models and the Modeling Cycle Dr.

Query Word Labeling and Back Transliteration for Indian Languages: MSRI Shared task system

Query Word Labeling and Transliteration for Indian Languages: IITP TS Shared Task system

Machine Transliteration in Code-Mixed Indian Social Media Text Hemanta Baruah (186155001) Ph.D

Approaches Based on guided code generation Based on exploring existing code Based on

Chaos- -Based Generation of Optimal Spreading Based Generation of Optimal Spreading Chaos

Chapter 11 Tree-based models Statistical Machine Translation Tree-Based Models Traditional

MDL-Based Models for Transliteration Generation . . . . . . 1 - PowerPoint PPT Presentation

. University of Helsinki July 30, 2013 SLSP 2013 J. Nouri, L. Pivovarova, R. Yangarber (UH) July 30, 2013 SLSP 2013 Department of Computer Science Javad Nouri, Lidia Pivovarova, and Roman Yangarber . MDL-Based Models for Transliteration

A Python Toolkit for Universal Transliteration . . . . . Ting Qian 1 , Kristy Hollingshead 2 ,

A Log-linear Block Transliteration Model based on Bi-Stream HMMs Bing Zhao Joint work with

Other models used to Model Demand Dr. Randa Oqab Mujalli TRIP GENERATION Dr. Randa Oqab Mujalli

ICTs in education Moving from 1 Generation to 2 Generation models a framework for program

Implicit Generation and Generalization with Energy Based Models Yilun Du and Igor Mordatch

Understorey identification through the generation of canopy base height models based on LiDAR

Cross-Language IR at University of Tsukuba Automatic Transliteration for Japanese, English, and

Distributed Generation of Random Graphs Based on Social Network Models Kyrylo Institute for

Transcription, transliteration, transduction, and translation A typology of crosslinguistic name

Automatic Code Generation from Stateflow Models Andres Toom IB Krates O / Institute of

Using Accessor Variety Features of Source Graphemes in Machine Transliteration of English to

Recurrent Neural Models: Language Models, and Sequence Prediction and Generation CMSC 473/673

LIGA and Syllabification Approach for Language Identification and Back Transliteration : Shared

Encoding transliteration variation through dimensionality reduction Parth Gupta 1 , Paolo Rosso 1

Translation &amp; Transliteration between Related Languages Anoop Kunchukuttan Mitesh Khapra

Code Generation Issues Aslan Askarov aslan@cs.au.dk Based on slides by E. Ernst

Model-Based Testing: Automated Generation of Test Cases, Test Data, and Test Procedures from

Agent-Based Modeling and Simulation Models, Agent-based Models and the Modeling Cycle Dr.

Query Word Labeling and Back Transliteration for Indian Languages: MSRI Shared task system

Query Word Labeling and Transliteration for Indian Languages: IITP TS Shared Task system

Machine Transliteration in Code-Mixed Indian Social Media Text Hemanta Baruah (186155001) Ph.D

Approaches Based on guided code generation Based on exploring existing code Based on

Chaos- -Based Generation of Optimal Spreading Based Generation of Optimal Spreading Chaos

Chapter 11 Tree-based models Statistical Machine Translation Tree-Based Models Traditional

Translation & Transliteration between Related Languages Anoop Kunchukuttan Mitesh Khapra