Information Systems for Indian Languages

Name: Information Systems for Indian Languages | International Conference, ICISIL 2011, Patiala, India, March 9-11, 2011. Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

International Conference, ICISIL 2011, Patiala, India, March 9-11, 2011. Proceedings

Chandan Singh Gurpreet Singh Lehal Jyotsna Sengupta Dharam Veer Sharma Vishal Goyal(Herausgeber*in)

Springer (Verlag)

Erschienen am 11. Februar 2011

XVI, 318 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-19403-0 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Title Page
Preface
Organization
Table of Contents
Oral
A Novel Method to Segment Online Gurmukhi Script
Introduction
Characteristics of Gurmukhi
Data Capture and Preprocessing
Proposed Segmentation Algorithm
Extraction of Strokes
Merging of Substrokes
Results, Discussions and Future Scope
References
Automatic Speech Segmentation and Multi Level Labeling Tool
Introduction
System - Overview
Feature Extraction
Initialization of HMM Models
Training the Models
Fixing the Silence Models
Phone Labeling
Syllable Labeling
Converting to SFS Format
Performance Results
Conclusion
References
Computational Aspect of Verb Classification in Malayalam
Introduction
Verb Classification of Prof. A.R. Rajaraja Varma (ARR)
Verb Classifications by Prof. Suranad Kunjan Pillai (SKP)
Conclusions
References
Period Prediction System for Tamil Epigraphical Scripts Based on Support Vector Machine
Introduction
System Overview
Preprocessing
Binarization
Thinning
Efficient Segmentation Method for the Proposed Methodology
Feature Extraction Phase
Classification and Period Prediction
Performance of the System
Conclusion
References
Name Entity Recognition Systems for Hindi Using CRF Approach
Introduction
Related Work for Indian Languages
Experiment Setup
Named Entity Tagset
Tagging Scheme
Named Entity Feature
Training and Test Set Collection
Evaluation and Results
Conclusion
References
An N-Gram Based Method for Bengali Keyphrase Extraction
Introduction
Description of the Corpus
Proposed Method
Candidate Keyphrase Identification
Calculating Scores for Keyphrase Candidates
Extracting Keyphrases
Comparisons to Existing Methods
Evaluation and Experimental Results
Results
Conclusion and Future Work
References
Feature Extraction and Recognition of Bengali Word Using Gabor Filter and Artificial Neural Network
Introduction
Gabor Filter
Present Work
Image Preprocessing
Generation of Bengali Dictionary Pages
Thinning and Normaalization of Each Boxed Word
Feature Extraction and Calculation for Each Word Using Gabor Filter
Training ANN Using Back Propagation Algorithm
Results
References
The Segmentation of Half Characters in Handwritten Hindi Text
Introduction
Related Work
Database
Characteristics of Hindi Language
Segmentation of Half Characters
Results
Discussion
References
Finding Influence by Cross-Lingual Blog Mining through Multiple Language Lists
Introduction
Overview
Understanding Influence
Information Retrieval
Cross Lingual Search
Preliminary Results
Data Collection
Sample NE Extracted and Their Influence Scores
Search Results
Related Work
Conclusion and Future Work
References
Renaissance of Opinion Mining
Introduction
Related Work
Conclusion
References
OpenLogos Machine Translation: Exploring and Using It in Anusaaraka Platform
Introduction
Extracting Informations from OpenLogos System
Part of Speech (POS)
Extracting Parse Information
Conclusion
References
Role of e-Learning Models for Indian Languages to Implement e-Governance
Introduction
Role of e-Learning in e-Governance Implementation
e-Learning and e-Governance in India
Action Plans to Implement e-Learning and e-Governance
Conclusion
References
A Compiler for Morphological Analyzer Based on Finite-State Transducers
Introduction
Finite State Transducers
Morphological Dictionary
The Compiler
Experiments and Comparisons
Concluding Remarks
References
On Multifont Character Classification in Telugu
Character Classification
Features and Classifiers
Results and Discussions
Conclusions
References
Parallel Implementation of Devanagari Document Image Segmentation Approach on GPU
Introduction
Introduction to nVidia CUDA
Proposed Segmentation Method
Sequential and Parallel Implementation of Line Segmentation Method
Sequential and Parallel Implementation of Word Segmentation Method
Results and Discussions
Conclusion
References
A Rule Based Schwa Deletion Algorithm for Punjabi TTS System
Introduction
Punjabi Language and Schwa
Schwa Deletion Algorithm
Module I: Vowel-Consonant Pattern Generation
Module II: Schwa Deletion (/insertion) in Vowel-Consonant Patterns
Algorithm
Performance Analysis
Conclusions
References
Clause Based Approach for Ordering in MT Using OpenLogos
Introduction
Anusaaraka
OpenLogos Diagnosis File
Existing Approach
Proposed Approach
Approach
Algorithm
Description of Algorithm Using Example
Conclusion and Future Work
References
Comparison of Feature Extraction Methods for Recognition of Isolated Handwritten Characters in Gurmukhi Script
Introduction
Literature Survey
Feature Extraction Methods
Zoning
Directional Distance Distribution
Gabor
Classification Methods
Results and Discussions
Reasons of Failure
References
Dewarping Machine Printed Documents of Gurmukhi Script
Introduction
Previous Work
Proposed Solution
Experimental Results
Conclusion
References
Developing Oriya Morphological Analyzer Using Lt-Toolbox
Introduction
Related Works
Design
Paradigm Approach
Current Dictionary
Source for Database
Experiment and Results
Coverage of Verbs
Total Coverage
Error Analysis
Conclusion and Future Work
References
Durational Characteristics of Indian Phonemes for Language Discrimination
Introduction
Database and Labeling
Analysis
Conclusion
References
A Transliteration Based Word Segmentation System for Shahmukhi Script
Introduction
Shahmukhi Script
Word Boundary Issues in Shahmukhi Text
Space Insertion Problem
Space Omission Problem
Algorithm for Handling Space Insertion Problem
Algorithm for Handling Space Omission Problem
Experiments and Results
References
Optimizing Character Class Count for Devanagari Optical Character Recognition
Introduction
Problems with Segmentation (Need of Multiple Classes)
Identification/Optimization of the Classes
Conclusion
References
Multifont Oriya Character Recognition Using Curvelet Transform
Introduction
The Curvelet Transform
Sub-band Decomposition.
Smooth Partitioning
Renormalization
Ridgelet Analysis
The Proposed Method
Experiments and Results
Conclusions
References
Exploiting Ontology for Concept Based Information Retrieval
Introduction
Ontology Based Model for Concept Based Information Retrieval
Algorithm for Identifying Concept Clusters
Conclusion
References
Parsing of Kumauni Language Sentences after Modifying Earley's Algorithm
Introduction
Earley's Parsing Algorithm
Derivation of Kumauni Language Grammar and Modification of Earley's Algorithm
Modification of Earley's Algorithm for Kumauni Text Parsing
Parsing Kumauni, Using Proposed Grammar and Algorithm
Stages of The Model
Verification of Program
Conclusion and Future Work
References
Comparative Analysis of Gabor and Discriminating Feature Extraction Techniques for Script Identification
Introduction
Gabor Filters
Discriminating Features of Punjabi Words and English Numerals
Classification
Experimental Results and Discussion
References
Poster
Automatic Word Aligning Algorithm for Hindi-Punjabi Parallel Text
Introduction
Word Alignment
Related Work
Alignment Algorithm
Algorithm
Comparison
Evaluation and Results
Conclusion
References
Making Machine Translations Polite: The Problematic Speech Acts
Introduction
The Corpus and the Situations
Classifying the Problematic Speech Acts
Problematic Speech Acts in Situation 2
Problematic Speech Acts in Situation 4
Conclusion and the Way Ahead
References
Tagging Sanskrit Corpus Using BIS POS Tagset
Introduction
Sanskrit POS Tagging
Availability of Various POS Tagsets
Tagging Sanskrit Using the BIS Tagset
Conclusion
References
Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach
Introduction
Linguistic Transliteration Scheme
Model and Algorithm
Experiment and Evaluation
Conclusion
References
Online Handwriting Recognition for Malayalam Script
Introduction
Malayalam Script
Challenges
Data Collection and Analysis
Pre-processing
Feature Extraction
Classification and Recognition
Post Processing
Results
References
Optimized Multi Unit Speech Database for High Quality FESTIVAL TTS
Introduction
Multi Unit Speech Database Creation
Corpus Collection and Processing
Letter to Sound Rules (LTS Rules)
Optimal Text Selection
Speech Database
Multi Unit Label for Speech Database
Building Voice and Synthesis
Conclusions
References
Comparative Analysis of Printed Hindi and Punjabi Text Based on Statistical Parameters
Introduction
Statistical Analysis
Results and Discussions
Word Length Analysis
Unigram Analysis
Bigram Analysis
Miscellaneous Analysis
Conclusion
References
Participles in English to Sanskrit Machine Translation
Introduction
Participles in English and Sanskrit
System Model of Our EST System
Implementation and Results
Conclusions and Future Scope
References
Web-Drawn Corpus for Indian Languages: A Case of Hindi
Introduction
Encoding of Hindi Content
"Hinglish"
Transliterated Texts
Machine-Translated Text
Collection Method
Text Variety
Text Quality
Conclusions
References
Handwritten Hindi Character Recognition Using Curvelet Transform
Introduction
Devanagari Script Characteristics
Proposed Approach
The Curvelet Transform
Feature Extraction Algorithm
Experimental Results and Discussion
Conclusion and Future Work
References
Challenges in Developing a TTS for Sanskrit
Introduction
TTS for Other Indian Languages
Requirements for the Sanskrit TTS
Text Processing, Normalization and Word/Sentence Recognition
Phonotactics and Prosody
Grapheme-to-Phoneme (G2P) Rules
Text Preparation, Sound Recording and Annotation
Conclusion
References
A Hybrid Learning Algorithm for Handwriting Recognition
Introduction
Division Point Distance Feature
Hybrid Learning Algorithm
Experiment
Conclusion
References
Hindi to Punjabi Machine Translation System
System Architecture
Evaluation and Results
Comparison with Other Existing Systems
Conclusion
References
Cascading Style Sheet Styling Issues in Punjabi Language
Introduction
Analysis of Different Styling Issues
Styling of First Letter
Underlining of the Characters
Link Displayed While Mouse Over
Over Lining of the Characters in Different Browsers
Line-through of the Characters
Horizontal Spacing
Title Bar Display for Punjabi Letters
Conclusion and Future Work
References
Translation of Hindi se to Tamil in a MT System
Introduction
Case Marking Pattern in Hindi and Tamil
Distribution of $se$ in Hindi
Rules for Disambiguation of $se$
Results and Discussion
Conclusion
References
Preprocessing Phase of Punjabi Language Text Summarization
Introduction to Text Summarization
Pre Processing Phase of Punjabi Text Summarization
Punjabi Language Stop Word Elimination
Punjabi Language Noun Stemming
Finding Common English-Punjabi Noun Words from Punjabi Corpus
Finding Punjabi Language Proper Nouns from Punjabi Corpus
Identification of Cue Phrase in a Sentence
Pre Processing Algorithm for Punjabi Text Summarization
Conclusions
References
Comparative Analysis of Tools Available for Developing Statistical Approach Based Machine Translation System
Introduction to SMT
Steps in Statistical Machine Translation
Overview of Available Tools for Developing Statistical Machine Translation System
Complete Toolkits
Language Modeling Tools
Translation Modeling Tools
Decoders
Evaluation Tools
Comparison of Some of the Available Toolkits
Conclusion
References
Discriminative Techniques for Hindi Speech Recognition System
Introduction
Working of ASR
Discriminative Techniques in Statistical Framework
Analysis of Conventional Statistical Methods
Discriminative Techniques
Experimental Results
Experiment with Discriminative Techniques
Experiment with Modeling Units
Conclusion
References
An Experiment on Resolving Pronominal Anaphora in Hindi: Using Heuristics
Introduction
Experiment and Methodology
Architecture of Framework
Data for Experiment
Methodology and Procedure
Observations and Conclusions
Future Work
References
A Novel GA Based OCR Enhancement and Segmentation Methodology for Marathi Language in Bimodal Framework
Introduction
Related Work
Algorithm
Standard GA Based Algorithm
Proposed Algorithm
Results
Conclusion
References
Panmozhi Vaayil - A Multilingual Indic Keyboard Interface for Business and Personal Use
Introduction
Objective
Motivation
Existing Works and What They Offer
What Indic-Keyboards (Panmozhi Vaayil) Offers
Design
User Interface and Shell Extension
Capturing the Keyboard Events
XML Based Unicode Processing
Unicode Rendering
Implementation
Performance and Conclusion
References
Power Spectral Density Estimation Using Yule Walker AR Method for Tamil Speech Signal
Introduction
Evaluation of Windowing Methods
PSD Estimation for Tamil Speech Signal
Non Parametric Welch Method
Parametric Yule-Walker AR
Performance Evaluation
Conclusion
References
Challenges in NP Case-Mapping in Sanskrit Hindi Machine Translation
Introduction
Nature of Sanskrit and Hindi
Contrast between Sanskrit and Hindi Case Marking
Conclusion
References
Modified BLEU for Measuring Performance of a Machine-Translation Software
Introduction
Modifications to a BLEU Score
An Experiment Involving Saakava, an English-Marathi Machine Software
Concluding Remarks
References
Demo Abstracts
A System for Online Gurmukhi Script Recognition
Spoken Isolated Word Recognition of Punjabi Language Using Dynamic Time Warp Technique
Text-To-Speech Synthesis System for Punjabi Language
Hand-Filled Form Processing System for Gurmukhi Script
Urdu to Hindi and Reverse Transliteration System
About the System
iPlugin: Indian Language Web Application Development Tool
An OCR System for Printed Indic Scripts
Gujarati Text - To - Speech System
Large Web Corpora for Indian Languages
References
Localization of EHCPRs System in the Multilingual Domain: An Implementation
System Architecture
System Working
Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken