26 Hits in 5.3 sec

Towards automating the generation of derivative nouns in Sanskrit by simulating Panini [article]

Amrith Krishna, Pawan Goyal
2015 arXiv   pre-print
Every rule group has a head rule and the head rule notifies all the direct member rules of the group about the environment which contains all the details about data entities, participating in the derivation  ...  The proposed system follows a completely object oriented approach, that models each rule as a class of its own and then groups them as rule groups.  ...  Pavankumar Satuluri and Mr. P Sanjeev for participating in the system evaluation we had conducted and also for sharing their valuable comments.  ... 
arXiv:1512.05670v2 fatcat:qccu4hhwtzfxtofjoighorpmla

Analysis of Sanskrit Text: Parsing and Semantic Relations [chapter]

Pawan Goyal, Vipul Arora, Laxmidhar Behera
2009 Lecture Notes in Computer Science  
A computational grammar based on the framework of Panini is being developed. A linguistic generalization for Verbal and Nominal database has been made and declensions are given the form of DFA.  ...  Given a Sanskrit text, the parser identifies the root words and gives the dependency relations based on semantic constraints.  ...  Acknowledgment We humbly acknowledge our gratitude to revered Aacharya Sanskritananda Hari, founder and director of Kaushalya pitham Gurukulam, Vadodara for educating us in all aspects of Sanskrit language  ... 
doi:10.1007/978-3-642-00155-0_7 fatcat:5giul7udajfrxmumtscthajwai

English-Bhojpuri SMT System: Insights from the Karaka Model [article]

Atul Kr. Ojha
2019 arXiv   pre-print
It also discusses the impacts of the Karaka model in NLP and dependency parsing. It compares Karaka dependency and Universal Dependency.  ...  It also presents a brief idea of the implementation of these models in the SMT system for English-Bhojpuri language pair.  ...  ACKNOWLEDGEMENTS This thesis is a fruit of love and labour possible with the contributions made by many people, directly and indirectly. I would like to express my gratitude to all of them.  ... 
arXiv:1905.02239v1 fatcat:yqkyuzss3bfg3ddpswpfec3qg4

Neural Machine Translation System for English to Indian Language Translation Using MTIL Parallel Corpus: Special Issue on Natural Language Processing

B. Premjith, M. Anand Kumar, K.P. Soman
2019 Journal of Intelligent Systems  
Evaluation of the obtained models was performed both automatically and manually.  ...  We also collected sentences from different sources and cleaned them to make four parallel corpora for each of the language pairs, and then used them to model the translation system.  ...  Anusaaraka [5, 7] was another initiative put forward by the Indian Institute of Technology, Kanpur, which used the principles of Paninian Grammar for translation.  ... 
doi:10.1515/jisys-2019-2510 fatcat:izu7zhjhbrexxpvwg4tae4ah4y

Unsupervised learning of morphology without morphemes

Sylvain Neuvel, Sean A. Fulop
2002 Proceedings of the ACL-02 workshop on Morphological and phonological learning -  
The accuracy (precision) of the generated new words is as high as 80% using the pure Whole Word theory, and 92% after a post-hoc adjustment is added to the routine.  ...  The first morphological learner based upon the theory of Whole Word Morphology (Ford et al., 1997) is outlined, and preliminary evaluation results are presented.  ...  In Whole-Word Morphology, any morphological relation can be represented by a rule of the following form: (1) |X| α ↔ |X | β in which the following conditions and notations are employed: 1.  ... 
doi:10.3115/1118647.1118651 dblp:conf/sigmorphon/NeuvelF02 fatcat:xd7lsyrzkfd7tdsiu44t7wqczu

Unsupervised Learning of Morphology without Morphemes [article]

Sylvain Neuvel, Sean A. Fulop
2002 arXiv   pre-print
The accuracy (precision) of the generated new words is as high as 80% using the pure Whole Word theory, and 92% after a post-hoc adjustment is added to the routine.  ...  The first morphological learner based upon the theory of Whole Word Morphology Ford et al. (1997) is outlined, and preliminary evaluation results are presented.  ...  In Whole-Word Morphology, any morphological relation can be represented by a rule of the following form: (1) |X | α ↔ |X ′ | β in which the following conditions and notations are employed: 1.  ... 
arXiv:cs/0205072v1 fatcat:64uj3yhpsbastfjmyjrffkrwxi

Urdu-English Machine Transliteration using Neural Networks [article]

Usman Mohy ud Din
2020 arXiv   pre-print
This approach is tested on three models of statistical machine translation (SMT) which include phrasebased, hierarchical phrase-based and factor based models and two models of neural machine translation  ...  In such scenarios, translation of word is not only enough in order provide the correct/quality translation. Transliteration is a way to consider the context of word/sentence during translation.  ...  The word "Urdu" itself is derived from Turkish. Urdu is the national language of Pakistan and one of official language in India and Jammu Kashmir.  ... 
arXiv:2001.05296v1 fatcat:5zgacud2dfg5jiuzock7x5l4tq

Phonological Ontology (version 1) [article]

David Odden
2021 Zenodo  
A metatheoretical framework for theory construction and evaluation in phonology.  ...  constituted the Paninian theory of "natural class".  ...  "Identity" then states a condition on instances of nodes of a type in the SD, and refers to conditions on a rule "applying".  ... 
doi:10.5281/zenodo.5514164 fatcat:fpskluvaifdpjnaekp3caddlam

World Sanskrit Conference 2018 Vancouver, Canada : Abstracts

Adheesh Sathaye
2018 Zenodo  
It will also look briefly at the content of the sections that follow āsana, namely, the ṣaṭkarma, prāṇāyāma and ten mudrās.  ...  The paper will conclude by considering the question of the text's intended audience and its place in the broader history of medieval yoga.  ...  This blocks guṇa in bhid-Kta, but fails to block tiP from triggering guṇa in dhi-Śa-tiP.  ... 
doi:10.5281/zenodo.1476528 fatcat:phgs6zzwlnadrjt2j2ezgh4q6e

Paradigms regained: Theoretical and empirical arguments for the reassessment of the notion of paradigm [article]

Gabriele Diewald, Katja Politt
2022 Zenodo  
Paradigms in this sense are not only tools of morphological description but constitute the inherent structure of grammar.  ...  aiming to illustrate what the concept of grammatical paradigms can and cannot (yet) explain.  ...  Acknowledgements This work is also a part of the project The Middle Danish language in the light of a modern theory of grammaticalisation, grant DFF-7013-00045 from The Danish Council for Independent Research  ... 
doi:10.5281/zenodo.5506577 fatcat:bi7q3plqrvgdph4w5gsqa3lhaa

One-to-many-relations in morphology, syntax, and semantics

(:Unkn) Unknown, Universitätsbibliothek Der FU Berlin, Berthold Crysmann, Manfred Sailer
from the ideal of one-to-one correspondences, and develop formal accounts of the range of phenomena.  ...  interpretation of a full sentence) instead of deriving such structures step by step.  ...  (Paris, November 2014), and the workshop on building blocks (Leipzig, November 2014).  ... 
doi:10.17169/refubium-30780 fatcat:7zjavjkpe5amnlgo3ubd3y7l54

Parsing in Indian Languages

Kommaluri Vijayanand, L Ramamoorthy, Mca, L Ramamoorthy
Ph.D. (Linguistics) Editors Special   unpublished
as Maximum Entropy model), Grammar formalism used (such as Paninian framework) etc.  ...  Use and development of a variety programmes for the efficient use of computer and computing in these languages will be better achieved if we do the parsing of the syntactic and semantic structures of these  ...  CONCLUSION This attempt at the analysis of the cause-effect semantic relation in Tamil and the AVMs can be used in automatic identification of causal relations in text.  ... 


T Michael, W Halcomb
Stump (2011: 10) points out that this is essentially Panini's Principle (or: the Elsewhere Condition), that is, the idea that each cell or block in a paradigm has rules that become ranked.  ...  Hippisley (2016: 489-90) echoes this saying, "This is the elsewhere statement in lexical phonology, or Paninian default inference, and is used to resolve competition among rules.  ...  %Mor_Verb is the root node of the inheritance network %verb denotes the syntactical category %<roman> sets the path value to specified items (e.g. prefix followed by stem, etc.) and %each of these will  ... 

Investigations into Distributional Semantics for Cognate Detection and Phylogenetics

Diptesh Kanojia
Shared vocabulary facilitates second language learning and enables the computational models to perform cross-lingual learning for natural language processing (NLP) tasks.  ...  We also generate typological trees for Indian languages and, additionally, propose the division of the text into meaningful functional units which aid phylogenetic tree generation.  ...  We release our dataset (WNdata + PCdata) of cognate pairs publicly for the language pairs Hi -Mr, Hi -Pa, Hi -Gu, Hi -Bn, Hi -Sa, Hi -Ml, Hi -Ta, Hi -Te, Hi -Ne, and Hi -Ur.  ... 
doi:10.26180/14870082.v1 fatcat:w66zzisj35h7zgzzozssovneqy

The Nominal Inflectional Suffix -e(t) in Damascus Arabic: A Network Morphology Account [article]

Sameera Atiya Allihibi, University Of Calgary, University Of Calgary, Darin Flynn
For this language-specific syncretism, rules of referral are necessary to predict that the plural and feminine singular share a cell in the adjectival inflectional paradigm.  ...  This thesis is concerned with the nominal (noun and adjective) inflections in Damascus Arabic (DA). In particular, the focus is on the so-called feminine suffix -at ~ -et.  ...  block is in all cases resolved by the Pāṇinian Principle.  ... 
doi:10.11575/prism/28258 fatcat:hsok6jjhqjebdnoboklj3rxtmq
« Previous Showing results 1 — 15 out of 26 results