A statistical test useful in historical linguistics
نویسنده
چکیده
Riassunto: In linguistica storica occorrono metodi per quantificare la similarità fra lingue basandosi sul confronto di particolari liste di parole estratte dal vocabolario completo. In particolare, si pone il problema di valutare se il numero di elementi simili nelle due liste sia sufficientemente alto per rifiutare l’ipotesi di somiglianza casuale. Dopo aver illustrato un approccio già esistente in letteratura, in questo lavoro si propone una variante a tale metodologia illustrandone i vantaggi concettuali e applicativi.
منابع مشابه
The Impact of Genre-based Instruction of Narrative Texts on Iranian EFL Learners’ Motivation for Writing
This quasi-experimental study investigated the instructional efficacy of genre-based approach on Iranian EFL learners’motivation for writing. Out of 180 participants, 60 EFL male and female students at university level, with the age range of 19-28, based on a standard profeciency test, Preliminary English Test (PET), were selected and randomly assigned into control and experimental groups. Each...
متن کاملReading and Assessing the City / Neighborhood FabricAs a Text. Case Study: Sar-Tapulah Historical Neighbourhood inSanandaj
From a linguistic point of view, the city can be seen as a text, consisting of different components and structures being related to each other beyond a sentence. Looking at the city from this point of view, what establishes a syntactic relationship and cohesion and coherence of the components of the city as a common language is called the syntax of the city. Linguistic study of the text of the ...
متن کاملOCR Error Correction Using Statistical Machine Translation
In this paper, we explore the use of a statistical machine translation system for optical character recognition (OCR) error correction. We investigate the use of word and character-level models to support a translation from OCR system output to correct french text. Our experiments show that character and word based machine translation correction make significant improvements to the quality of t...
متن کاملReview of Statistics in Historical Linguistics Stephen Grimes
Introduction In this 1986 book, Sheila Embleton surveys the development and use of statistical techniques in historical linguistics. She argues that any successful lexicostatistic model must incorporate word borrowing rates. A computational model for family tree reconstruction using borrowing is introduced, building on ideas of Sankoff (Sankoff 1972). Embleton outlines future uses of lexicostat...
متن کاملMathematical and Computational Linguistics Project N.4 Syntactic Phylogenetic Trees
1. Linguistic Phylogenetic Trees The reconstruction of phylogenetic trees of language families is one of the main problems in Historical Linguistics. In recent years, computational methods have been used, mostly borrowed from similar techniques in mathematical biology, see for instance the collection of papers in [1]. Mostly, the computational reconstructions of linguistic phylogenetic trees fo...
متن کامل