ON KNOWLEDGE REPRESENTAnON USING SEMANTIC NETWORKS AND SANSKRIT
نویسندگان
چکیده
The similarity between the semantic network method of knowledge representation in artificial intelligence and shastric Sanskrit was recently pointed out by Briggs. As a step towards further research in this field, we give here an overview of semantic networks and natural-language understanding based on semantic networks. It is shown that linguistic case frames are necessary for semantic network processing and that Sanskrit provides such case frames. Finally, a Sanskrit-based semantic network representation is proposed as an interlingua for machine translation. I Th is material is based in part upon work supported by the Nat ional Science foundati on under Grant No. IST-8504713 (Ra paport) and in part by work supported by the Air Force Systems Command, Rome Atr Development Center, Grifliss Air Force Base. NY 13441 -5700. and the Air Force Office of Scientific Research. B011ing AFB. LX 20.\32 under contract No. F30602-85-C 0008 (Sribaril, SRIHARI, RAPAPORT, & KUMAR i I
منابع مشابه
Coarse Semantic Classification of Rare Nouns Using Cross-Lingual Data and Recurrent Neural Networks
The paper presents a method for WordNet supersense tagging of Sanskrit, an ancient Indian language with a corpus grown over four millenia. The proposed method merges lexical information from Sanskrit texts with lexicographic definitions from Sanskrit-English dictionaries, and compares the performance of two machine learning methods for this task. Evaluation concentrates on Vedic, the oldest lay...
متن کاملImproving the Morphological Analysis of Classical Sanskrit
The paper describes a new tagset for the morphological disambiguation of Sanskrit, and compares the accuracy of two machine learning methods (CRF, deep recurrent neural networks) for this task, with a special focus on how to model the lexicographic information. It reports a significant improvement over previously published results. 1 Challenges of Sanskrit Linguistics and Related Research Class...
متن کاملTwo Stage Neural Network model for Recognition of Indian Languages from Speech
India is a multilingual country. Officially about 20 languages are recognized by the government and there are about 500 languages spoken at different parts of the country. For developing the speech systems in Indian context, it is necessary to capture the language specific knowledge automatically from speech. Further it may be exploited for different speech tasks such as language identification...
متن کاملEmploying Automated Management to Administer a Large-Scale E-Science Cyber-Infrastructure
E-Science cyber-infrastructures empower broad ranges of users by hiding the complexity of accessing advanced underlying infrastructure including high performance computers, high-speed networks, data streams and sensor networks. But due to their scale, running these systems in production has raised major system management challenges. In this paper, we discuss challenges of managing one such e-sc...
متن کاملEmergence of Natural Language Lexicons: Empirical and Modeling Evidence from Homesign and Nicaraguan Sign Language
Where do we get language from? Clearly, it requires our human brains: a chimp exposed to a lifetime’s worth of language will not surpass a child who has only had a few years of exposure. But it also clearly requires something from the environment: language-deprived children clearly don’t spring forth speaking Hebrew, or Greek, or Sanskrit. What is it about the human learner, and about the envir...
متن کامل