1. SANSKRIT ANALYZING SYSTEM
Manji Bhadra, Surjit Kumar Singh, Sachin Kumar, Subash, Diwakar Mishra
Muktanand Agrawal, R.Chandrashekar,
Sudhir K Mishra, Girish Nath Jha
3rd ISCLS, Hyderabad

2. Introduction It is an attempt towards analysis of laukika Sanskrit
Major goal is to build a machine translation system from Sanskrit to other Indian language.
The modules have been developed separately
We need to integrate these modules
We need to evaluate these modules
3rd ISCLS, Hyderabad

3. Introduction
The system accepts full text inputs in Devanagari Unicode (UTF-8).
It supports two IMEs - Baraha and J-IME.
It has two major components-
the shallow parser
the kraka analyzer
3rd ISCLS, Hyderabad

4. Shallow parser The modules are as follows- sandhi analyzer
samsa analyzer *
subanta analyzer
gender analyzer
kdanta analyzer
taddhita analyzer*
tianta analyzer
POS tagger
* Modules are under development
3rd ISCLS, Hyderabad

5. How does it work
Show example
3rd ISCLS, Hyderabad

6. Our platform Java servlet based web application and services.
Java, JSP for frontend.
Unicode input/output with flatfiles, RDBMS (MS-SQL server 2005)
MS-JDBC driver for connectivity
Apache-Tomcat for web server
Javascript IME for unicode output with Itrans input
3rd ISCLS, Hyderabad

7. Sandhi analyzer
Sandhi processing is critical for any further processing of Sanskrit. Without sandhi-vichheda it is not possible to get the word constituents for analysis.
At present, our sandhi analyzer does only vowel sandhi splitting. The consonant splitting is under development.
Our goal is to be able to parse a very complex string with potentially all kinds of sandhi
3rd ISCLS, Hyderabad

8. Sandhi analyzer input Sanskrit text ↓ viccheda eligibility tests
(pre-processing)
subanta processing
search of sandhi marker and sandhi patterns
(‌‌sandhi rule base)
generate possible solutions
(result generator)
search the lexicon
(to parse the vibhakti of first segment, if any)
output (segmented text)
3rd ISCLS, Hyderabad

9. Sandhi analyzer 1. tokenize by space (words)
2. preprocess (exclude puncts)
-> puncts marked
3. check example base - if found stop
4. check subanta (it checks avyayas, verbs as well)
-> pratipadikas
-> avyayas marked
-> verbs marked
3rd ISCLS, Hyderabad

10. Sandhi Analyzer 5. check pratipadika list
-> if found then dont process for Sandhi
-> if not found then start sandhi processing
6. search of sandhi marker and sandhi patterns
7. generate possible solutions
8. search the lexicon
9. subanta processing (to parse the vibhakti of first segment, if any)
10. output (segmented text)
3rd ISCLS, Hyderabad

11. Live demo from JNU server
Demo from localhost
3rd ISCLS, Hyderabad

12. Subanta analyzer
Isolating the inflections and obtaining nominal bases and its case terminations is essential for morph analysis.
The system has Unicode Devanagari input/output mechanism and accepts complete text as well
3rd ISCLS, Hyderabad

13. Subanta analyzer INPUT TEXT ↓ PRE-PROCESSOR
VERB DATABASE  LIGHT POS TAGGING  AVYAYA DATABASE
SUBANTA RECOGNIZERVIBHAKTI DATABASE
SUBANTA RULES SUBANTA ANALYZER SANDHI RULES
SUBANTA ANALYSIS
3rd ISCLS, Hyderabad

14. Subanta Analyzer Works on a subanta rulebase and example-base
Subanta eligibility
check fixed lists (punctuations, avyayas, verbs)
If found  tag
Else mark them SUBANTA
Check it in dictionary
If found store separately
Else start subanta processing
3rd ISCLS, Hyderabad

15. Subanta Analyzer check example-base Template search
If found  tag else continue
Template search
Evaluate string as per set templates
Split it in parts and match the viccheda patterns
If found  obtain corresponding analysis
Else tag the input SUBANTA
3rd ISCLS, Hyderabad

16. Live demo from JNU server demo from localhost
3rd ISCLS, Hyderabad

17. Kdanta Analyzer
3rd ISCLS, Hyderabad

18. Kdanta Analysis
The process of kdanta analysis mechanism is divided into two sections - recognition and analysis.
The kdanta recognition starts by an exclusion process. The verb forms, avyayas and punctuations are excluded by running POS tagger
The nominal bases are obtained by the subanta analyzer These nominal bases are then checked in fixed lists. This may result in some of the subantas being marked for kdanta.
The remaining subantas are sent to the kdanta recognizer and analyzer system for recognition and analysis using following steps – 
3rd ISCLS, Hyderabad

19. Kdanta Analysis
check the kdanta database, annotated corpus and kdanta-tagged Monier Williams Sanskrit Digital Dictionary (MWSDD).
the subantas still untagged for kdanta are sent to the rule base for kdanta checking.
there may still remain an untagged kdanta subanta. This will count as failure of the system.
अधिकारी["अधिकारिन्","अधि+डुकृञ्","इनि","noun_m"]_KR
3rd ISCLS, Hyderabad

20. Tianta Analysis
The methodology is a mix of using verb database and reverse Paninian processing
pre-processing
take token by token
confirm the verb (dict, check suffixes), ignore others
Check database
If not found  start analysis
analyze suffixes
evaluate remaining string for base (dict check for bases)
result
3rd ISCLS, Hyderabad

21. POS Tagger Rule-based tagger is developed for Sanskrit Language.
There are three kinds of tags in this tagset- Word class main tags, feature sub-tags, punctuation tags.
The tag as a whole is a combination of word class main tag with feature sub-tags separated by an underscore
All the tags bear Sanskrit names with letter-digit acronymic in Roman script
Tagset (JNU server)
Tagset (localhost)
3rd ISCLS, Hyderabad

22. POS Tagger Input text Pre processing Fixed list tagger Morph analyzer
Disambiguator*
Result normalizer
Display tagged text
3rd ISCLS, Hyderabad

23. Gender Analyzer
Along with the information of vibhakti and number, it is also necessary to have information of gender. In Sanskrit there is agreement within noun phrase in terms of vibhakti, number and gender. While translating a Sanskrit sentence into Hindi, it is necessary to know what would be collocational gender of the sentence, otherwise the whole translation may be wrong.
3rd ISCLS, Hyderabad

24. Gender Analyzer Input Sanskrit text Un-anlayzed Text
Lexical lookup
Un-anlayzed Text
Application of Subanta Analyzer
Lexical lookup
Subanta Analyzed Text
Un-analyzed text
Application of rulebase
Check gender agreement within a
noun phrase
Suggest the gender of the noun phrase for Hindi translation
3rd ISCLS, Hyderabad

25. live demo from JNU server demo from localhost
3rd ISCLS, Hyderabad

26. Kraka Analyzer VERB ID VERB ANALYSIS NON—VERB ID SUBANTA ANALYSIS
VERB ID
VERB ANALYSIS
NON—VERB ID
SUBANTA ANALYSIS
KK CHECK*
KRAKA RULES*
SPECIAL CONDITIONS
KRAKA ASSIGNMENT
3rd ISCLS, Hyderabad

27. Conclusion
The authors in this paper have presented an ongoing work for developing a complete SAS. Currently, the SAS has some modules partially developed and some under development.
Significant future additions will be the
Taddhita, samasa modules
ambiguity resolution modules
System integration module
Evaluation module
3rd ISCLS, Hyderabad

28. Thank You!
3rd ISCLS, Hyderabad