{"title":"Dating Sanskrit texts using linguistic features and neural networks","authors":"Oliver Hellwig","doi":"10.1515/if-2019-0001","DOIUrl":null,"url":null,"abstract":"Abstract Deriving historical dates or datable stratifications for texts in Classical Sanskrit, such as the epics Mahābhārata and Rāmāyaṇa, is a considerable challenge for text-historical research. This paper provides empirical evidence for subtle but noticeable diachronic changes in the fundamental linguistic structures of Classical Sanskrit, and argues that Classical Sanskrit shows enough diachronic variation for dating texts on the basis of linguistic developments. Building on this evidence, it evaluates machine learning algorithms that predict approximate dates of composition for Sanskrit texts. The paper introduces the required background, discusses the relevance of linguistic features for temporal classification, and presents a text-historical evaluation of Book 6 of the Mahābhārata, whose historical stratification is disputed in Indological research.","PeriodicalId":13385,"journal":{"name":"Indogermanische Forschungen","volume":null,"pages":null},"PeriodicalIF":0.1000,"publicationDate":"2019-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/if-2019-0001","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Indogermanische Forschungen","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1515/if-2019-0001","RegionNum":3,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"N/A","JCRName":"LANGUAGE & LINGUISTICS","Score":null,"Total":0}
引用次数: 6
Abstract
Abstract Deriving historical dates or datable stratifications for texts in Classical Sanskrit, such as the epics Mahābhārata and Rāmāyaṇa, is a considerable challenge for text-historical research. This paper provides empirical evidence for subtle but noticeable diachronic changes in the fundamental linguistic structures of Classical Sanskrit, and argues that Classical Sanskrit shows enough diachronic variation for dating texts on the basis of linguistic developments. Building on this evidence, it evaluates machine learning algorithms that predict approximate dates of composition for Sanskrit texts. The paper introduces the required background, discusses the relevance of linguistic features for temporal classification, and presents a text-historical evaluation of Book 6 of the Mahābhārata, whose historical stratification is disputed in Indological research.
期刊介绍:
Indogermanische Forschungen publishes contributions (essays and reviews) mainly in the areas of historical-comparative linguistics, historical linguistics, typology and characteristics of the languages of the Indogermanic language family. Essays on general linguistics and non-Indogermanic languages are also featured, provided that they coincide with the main focus of the journal with respect to methods and language history.