Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info

New from Oxford University Press!


Oxford Handbook of Corpus Phonology

Edited by Jacques Durand, Ulrike Gut, and Gjert Kristoffersen

Offers the first detailed examination of corpus phonology and serves as a practical guide for researchers interested in compiling or using phonological corpora

New from Cambridge University Press!


The Languages of the Jews: A Sociolinguistic History

By Bernard Spolsky

A vivid commentary on Jewish survival and Jewish speech communities that will be enjoyed by the general reader, and is essential reading for students and researchers interested in the study of Middle Eastern languages, Jewish studies, and sociolinguistics.

New from Brill!


Indo-European Linguistics

New Open Access journal on Indo-European Linguistics is now available!

Academic Paper

Title: Towards a Computational Analysis System for Sanskrit
Author: Subhash Chandra
Email: click here to access email
Institution: Centre for Development of Advanced Computing
Linguistic Field: Computational Linguistics; Lexicography; Translation
Subject Language: Sanskrit
Abstract: The paper presents a computational analysis model for Sanskrit text based on Paanini’s rule system and associated corpora. The model includes reverse processing in the following order:

Input text
[upload file or cut-paste text in
text-area component]
charset check non Unicode discontinue
language check not Sanskrit discontinue
connect to ti_anta db export
verbs into a text file
tag verbs verbs not found
proceed to next step
[reverse derivation/duplication
for complex verb forms]
connect to subanta db export
avyaya data
check for avyayas tag them
connect to subanta db export
vibhakti data
check vibhaktistag nps for
yogyata check
karaka semantics check
karaka-vibhakti analysis
output text

Sanskrit is a highly inflected language where a syntactic constituent is defined as supti_antam padam. A sentence will have one or more of these padas under the karaka control. Cardona (1988) posits the following formula for sentences – ( N – En )p . . . (V – Ev )

After suP and ti_ combine with pratipadikas, they are assigned syntactico-semantic relation by the karaka stipulations to return complete sentences. The pada morphology in Sanskrit is very complex. The noun phrases or the suP padas are formed by adding one of the 21 suP (nominal inflection) suffixes (according to number/gender information) to the nominal bases (pratipadikas). The latter can potentially include serial derivational sub-constituents like - k_t (primary derivation), taddhita (secondary derivation) , samas (compounding) and stripratyayas (feminine forming affixes). At each stage of these intermediate derivational processes, there could be samhita (continuum) situation leading to sandhi (morphophonemic combination of compatible sounds). Sanskrit verbs too are very complex. Besides the regular lakara forms, there could be derived and reduplicated verb forms - _ijanta (causative – _ic), sannata (expressing desire – san, kyac, kamyac, kvip, kya_, kya_, _i_, yak, ay and iya_) , ya_anta (duplicated – ya_ and ya_lu_anta). Further, these can have atmane and parasmai forms in 10 lakaras and 3 x 3 person and number combinations, and can also be potentially prefixed with 22 prefixes. Finally there could be innumerable namadhatus (nominalized verbs). Mishra & Jha (2005) have drawn the following distribution of Sanskrit verbs - VR [2000]
_ san
_ kyac
_ kamyac
_ kvip
_ kya_
_ kya_
_ _i_
_ _ic
_ ya_
_ yak
_ ay
_ iya_
+ one normal form

Ten lakar [10 lakaras]
parasmai atmane
_ _
10x9 forms 10x9 forms
_ _
22 upasarga 22 upasarga

The importance of such a system can be understood by the fact that no translation system from Sanskrit to Indian languages can be developed without first completing the analysis part. The paper gives details of each component required, and current developments. The principal author at a national seminar on Translation Today presented an earlier version of the paper: state and issues, deptt. Of linguistics, university of Kerala, Trivandrum last year. The present version includes some of the newer research and algorithm tune-ups. In particular, the paper focuses on the following components –
Building linguistic resources for translation Reverse Sandhi module for initial segmentation, POS tagging module, Verb inflection morphology (ti_anta) analysis module, Nominal Inflection morphology (subanta) analysis module, Derivational morphology (k_t, taddhita, stri, samasa) analysis module, Karaka analysis module.
Type: Individual Paper
Status: Completed
Venue: Mumbai, India
Publication Info: MSPLI, Mumbai Proceeding

Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page