Work at TACOLA Lab

1
Work at TACOLA Lab

• Team Members
• T.V.Geetha Ranjani Parthasarathi Madhan Karky
• E.UmaMaheswari J.Balaji Subalalitha
  Elanchezhiyan.K, Karthika, Thenmalar,
  Radhakrishnan, Kandasamy, Padmavathi, Aruna,
  Vijayavani

2
Tamil Language Processing

• Tamil Language Processing
• Morphological analyser
• Normal Words, Compound Words, Colloquial Words
• Parser
• Simple, Complex and Compound Sentences
• Semantic analysis based on UNL
• Language Technology
• Blog Mining
• Ontology Based Information Extraction
• Personalized Search
• Parallelization for NLP Processing
• Emotion detection form text
• Carnatic Music Processing
• Raga Modelling
• Singer, Genre Identification
• Music Emotion Recognition

• Tamil Language Oriented Tools
• Dictionary
• Text Compaction
• UNL Based Work
• UNL for semantic representation
• Nested UNL
• Concept based Search
• Bi-lingual Search
• Event Processing
• Discourse Analysis
• Summarization
• Question answering
• Thirukural Search
• Lyric Oriented Processing
• Lyric Mining
• Lyrics for Tunes
• Pleasantness

3
Papers for TIC 2011

• Tamil Language Oriented Tools
• Agaraadhi A Novel Online Dictionary Framework
• An Efficient Tamil Text Compaction System.
  (Surukkupai)
• Kuralagam, A Concept Relation Based Search
  Framework for Thirukural.
• Popularity Based Scoring Model for Tamil Word
  Games
• Tamil Language Processing
• Template based Multilingual Summary Generation.
• On Emotion detection from Tamil Text.
• Tamil Summary Generation for Cricket Match.
• Lyric Oriented Processing
• Lyric Mining Word, Rhyme Concept
  Co-occurrence Analysis.
• Special Indices for LaaLaLaa Lyric Analysis
  Generation Framework.

4
AGARAADHIA NOVEL ONLINE DICTIONARY FRAMEWORK

• Elanchezhiyan.K
• Karthikeyan.S
• T.V.Geetha
• Ranjani Parthasarathi
• Madhan Karky

5
OBJECTIVES

• Agaraadhi, a dictionary framework for indexing
  and retrieving Tamil words, their meaning,
  analysis and related information.
• Framework to incorporate various unique features
  - designed to provide additional information to
  the user regarding the word that they query
  about.

6
INTRODUCTION

• Agaraadhi dictionary has more than 3 lac words in
  various domains such as
• General,
• Literature,
• Medical,
• Engineering,
• Computer Science,
• Birds Name and More
• The Agaraadhi is a Tamil English bilingual
  dictionary.

7
INTRODUCTION CONT

• The Agaraadhi is a Tamil English bilingual
  dictionary with 20 features. such as
• morphological analysis,
• morphological generation,
• word usage statistics,
• word pleasantness analysis,
• spell checking,
• similar word finder,
• word usage in literature,
• picture dictionary,
• number to text conversion,
• phonetic transliteration,
• live usage analysis from micro blogs and more

8
AGARAADHI FRAMEWORK CONT
9
AGARAADHI FEATURES

• Morphological Analyser
• gives the morphological features of the query
  word such as root word, parts of speech, gender,
  tense and count.
• If the Query word is padithaan, Morphological
  Analyser gives as padi as root, word represents
  male gender and query word is past tense and so
  on.
• Morphological GeneratorTamil morphological
  generator tackles different syntactic categories
  such as nouns, verbs, post positions, adjectives,
  adverbs.
• The generator is used to generate possible
  morphological variations of the query word.
• Spell Checker
• used to check the spelling of Tamil words and to
  provide alternative suggestions for the wrongly
  spelt words.
• If root word not in dictionary - generates all
  the possible suggestions with minimum variations
  from the given word

10
AGARAADHI FEATURES

• Word Suggestions
• gives the list of equivalent or related words for
  the given query word.
• Word Pleasantness
• score generator provides how easy it is to
  pronounce the word.
• Word Popularity Score
• shows the word usage in the web based on
  frequency distribution of the word across the
  popular blogs, news articles, social nets etc.
• Word Usage Statistics
• shows the usage of the word in the social network
  over the past one week.
• Word Usage in Literature
• finds the usage of words in popular literature
  such as Thirukural, Bharathiyar Padalgal, Avvai
  songs and also Lyrics of Tamil Movie songs.

11
AGARAADHI FEATURES

• Word of the Day
• A rare word is randomly chosen and is displayed
  in the opening page to facilitate users to learn
  a new word every day.
• Number to Text Converter
• converts a number to Tamil word equivalent as
  well as in English text. For example in Tamil we
  represent oru Arpputham (????????) for 100
  million, Kumbam (???????) for 10 billion and
  finally up to Anniyan (????????) for one zilli
• Picture Dictionary
• Pictures, photos or line drawings to depict
  popular words have been included in the
  dictionary to enable efficient learning for
  children using this tool.

12
RESULTS

• Query word pookkal (???????)
• http//www.agaraadhi.com/dict/OD.jsp?wE0AEAAE
  0AF82E0AE95E0AF8DE0AE95E0AEB3E0AF
  8DlntaSubmit.x8Submit.y7
• Query word mazhai (???)
• http//www.agaraadhi.com/dict/OD.jsp?wE0AEAEE
  0AEB4E0AF88lntaSubmit.x21Submit.y4
• Query word fruit
• http//www.agaraadhi.com/dict/OD.jsp?wfruitlnen
  

13
FUTURE WORK

• Providing APIs for programmers and developing
  mobile apps for Agaraadhi framework will open a
  good platform for many researchers and developers
  working in Tamil Computing area.

14
REFERENCE

• Anandan, R. Parthasarathi, and Geetha,
  Morphological Analyser for Tamil. ICON 2002,
  2002.
• Anandan, R. Parthasarathi, and Geetha,
  Morphological Generator for Tamil. Tamil Inayam,
  Malaysia, 2001.
• J. Jai Hari Raju, P. IndhuReka, Dr. Madhan Karky,
  Statistical Analysis and  visualization of Tamil
  Usage in Live Text Streams, Tamil Internet
  Conference, Coimbatore, 2010.

15
An Efficient Tamil Text Compaction System

• N.M.Revathi
• G.P.Shanthi
• Elanchezhiyan.K
• T V Geetha
• Ranjani Parthasarathi
• Madhan Karky

16
OBJECTIVES

• Why Compacting?
• limited message length in blog sites and tiny
  user interface of mobile phones.
• saves online storage space and hence reduction in
  cost.
• The paper proposes
• a text compaction system for Tamil, first of its
  kind in Tamil.
• Idea of compaction
• Getting the shortest word has no specific rule it
  is mainly aimed at understanding.
• can be obtained by omitting letters, replacing
  prefix and suffix through suitable symbols and
  numbers.

17
FRAMEWORK ARCHITECTURE

18
FRAMEWORK CONT..

• Input Processing
• The morphological analyzer removes the suffix (if
  present) added to the word and delivers the root
  word (RW).

19
FRAMEWORK CONT..

• Identification of the category Extraction of
  compact word
• Three categories of words common Tamil words,
  abbreviations/acronyms, numbers.
• abbreviations /acronyms by comparing it with the
  keys of the hashmap.
• With the help of the hash key and a mapping
  algorithm, the compact word is retrieved.
• Otherwise belongs to either the common tamil word
  or numbers
• If numbers - Numerical analyser for text to
  number conversion.
• Output Processing
• Tamil tool Morphological Generator to add the
  suitable suffix to cater to the rules of the
  language.

20
RESULT AND ANALYSIS

• Tested with over 10,000 words.
• The final result is reduced to 40 of the
  original text.

21
REFERENCES

• Anandan, R. Parthasarathi, and Geetha,
  Morphological Analyser for Tamil. ICON 2002,
  2002.
• Fung, L. M. (2005). SMS short form identification
  and codec. Unpublished masters thesis, National
  University of Singapore, Singapore . 
• Acrophile (LSLarkey, P Ogilvie, MA Price, B
  Tamilio, 2000) a system that automatically
  searches acronym expansion pairs.
•   Short Message Service (SMS) Texting Symbols A
  Functional Analysis of 10,000 Cellular Phone Text
  Messages by Robert E. Beasley,Franklin College.
•  

22
Kuralagam - Concept Relation based Search Engine
for Thirukkural

• Elanchezhiyan.K
• T.V.Geetha
• Ranjani Parthasarathi
• Madhan Karky

23
Objectives

• Kuralagam is a conceptual search framework for
  Thirukkural based on UNL Framework.
• Searching with keywords in kurals and
  intepretations
• Concept based search based on CoReX conceptual
  indexing based on UNL
• Bilingual search English and Tamil
• Showing Relationships between the concepts.

24
Kuralagam Framework
25
Offline Processing

• Web Crawler
• A Thirukkural statistics crawler
• crawls the news and blog documents - to find the
  usage of each individual Thirukkural.
• The usage recorded for measuring the popularity
  score for each Thirukkural
• Enconversion Based on UNL
• Indexed based on CoReX Framework

26
UNL Enconversion

• UNL is an intermediate language
• processes knowledge across languagebarriers.
• captures semantics by converting natural language
  terms present in the document to concepts.
• concepts are connected to the other concepts
  through UNL relations - 46 UNL relations
• plf(Place From), plt(Place To), tmf(Time from),
  tmt(Time to) etc
• Process of converting a natural language text to
  UNL graph is known as Enconversion
• reverse process is known as Deconversion.

27
An Example speaks more...

• ExJohn was playing in the garden

28
Indexer

• The Kuralagam Indexer is designed based on CoReX
  Techniques.
• The Indexer stores and manages the UNL graphs in
  two different indices.
• Concept only index (C index), and
• Concept-Relation-Concept index (CRC index)

29
Online Processing

• Query Translation and Expansion
• converts the user query to UNL graph.
• uses CRC (Concept Relation Concept) CoReX indices
  to fetch similarity thesaurus and co-occurrence
  list to populate the Multi list Data Structure.
• Search and Ranking
• fetches the Thirukkural number and its details.
• Thirukkurals for a given query are fetched using
  the two types of concept relation indices namely
  CRC and C.
• The query concept is expanded using related CRC
  indices pointing to the query concept.
• helps in retrieving many Thirukkurals
  conceptually related to the query not possible
  with key word Thirukkural search engines.
• The ranking is based on
• priority to the indices in the order CRCgtC
• usage score
• frequency occurrence of the query concept

30
Tab Layout
31
Performance Evaluation

• The accuracy of the Thirukkural search engine was
  measured using the average precision and mean
  average precision.
• The comparisons between concept based search and
  keyword based search were measured using Average
  Precision methodology

32
Average Precision
33
Reference

• 1. Subalalitha, T V Geetha, Ranjani Parthasarathy
  and Madhan Karky Vairamuthu. CoReX A Concept
  Based Semantic Indexing Technique. In SWM-08.
  2008. India.
• 2. Foundation, U., the Universal Networking
  Language (UNL) Specifications Version 3 3ed.
  December 2004 UNL Computer Society, 2004.
  8(5).Center UNDL Foundation
• 3. Anandan, R. Parthasarathi, and Geetha,
  Morphological Analyser for Tamil. ICON 2002,
  2002.
• 4. T.Dhanabalan, K.Saravanan, and T.V.Geetha.
  2002. Tamil to UNL Enconverter, ICUKL, Goa,
  India.
• 5. Andrew, T. and S. Falk. User performance
  versus precision measures for simple search
  tasks. In 29th Annual international ACM SIGIR
  Conference on Research and Development in
  information Retrieval 2006. Seattle, Washington,
  USA.

34
Template Based MultiLingual Summary Generation

• Subalalitha C.N
• E.Umamaheswari
• T V Geetha
• Ranjani Parthasarathi
• Madhan Karky

35
Aim

• To generate a multi lingual summary using based
  on Universal Networking Language (UNL) Framework

36
The Architechture
37
Multi Lingual Summary Generation using UNL

• Template based Information Extraction
• Seven tourism specific templates have been
  designed and used
• Templates filled using semantic information
  inherent in UNL input graphs
• Template information is language independent and
  can be used with any desired language.

38
Example Templates for Tourism Domain
Template Semantics inherited from UNL
God iofgtgod, iofgtgoddess, iclgtgod
Food iclgtfood, iclgtfruit
Flaura and Fauna iclgtanimal, iclgtreptile, iclgtmammal, iclgt plant
Boarding facility iclgtfacility
Transport facility iclgttransport
Place iclgtplace, iofgtplace, iofgtcity, iofgtcountry
Distance icl gtunit , icl gtnumber
39
SummaryGeneration

• The template information is converted to target
  language using respective UNL-target language
  dictionaries.
• UNL-target language dictionaries contains root
  words.
• Natural language term from the root word is
  obtained using target language information like
  case suffixes and language technology tools like
  morphological generator
• (???????????????????)
• When these converted template information is
  fitted into target language specific dynamic
  sentence patterns, a summary is generated.

40
Performance Evaluation

• Tested with 33,000 Tamil and English text
  documents enconverted to UNL graphs.
• The performance of the methodology proposed has
  been evaluated using human judgement.
• The accuracy of the summary generated has
  achieved 90 .

• Further Enhancements
• Query specific summary
• Comparing the performance with human generated
  summaries.

41
References

• 1 Elanchezhiyan K, T V Geetha, Ranjani
  Parthasarathi Madhan Karky, CoRe Concept
  Based Query Expansion, Tamil Internet Conference,
  Coimbatore, 2010.
• 2 Alkesh Patel , Tanveer Siddiqui , U. S.
  Tiwary , A language independent approach to
  multilingual text summarization, Conference
  RIAO2007, Pittsburgh PA, U.S.A. May 30-June
  1,2007
• 3David Kirk Evans, Identifying Similarity in
  Text Multi-Lingual Analysis for Summarization ,
  Doctor of Philosophy thesis, Graduate School of
  Arts and Sciences , Columbia University, 2005
• 4 Radev, Allison, Blair-Goldensohn et al
  (2004), MEAD a platform for multidocument
  multilingual text summarization
• 5 The Universal Networking Language (UNL)
  Specifications Version 3 Edition 3, UNL Center
  UNDL Foundation December 2004.
• Jagadeesh J, Prasad Pingali, Vasudeva Varma,
  Sentence Extraction Based Single Document
  Summarization Workshop on Document
  Summarization, March, 2005, IIIT Allahabad.
• 7 Naresh Kumar Nagwani, Dr. Shrish Verma , A
  Frequent Term and Semantic Similarity based
  Single Document Text Summarization Algorithm
  International Journal of Computer Applications
  (0975 8887) Volume 17 No.2, March 2011 .
• 8Prof. R. Nedunchelian, Centroid Based
  Summarization of Multiple Documents Implemented
  using Timestamps First International Conference
  on Emerging Trends in Engineering and Technology,
  IEEE 2008