• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Python Library for Linguistic Typology

Student: Voronov Mikhail

Supervisor: Boris Orekhov

Faculty: Faculty of Humanities

Educational Programme: Fundamental and Computational Linguistics (Bachelor)

Final Grade: 8

Year of Graduation: 2019

Python programming language is widely used by linguists. In this thesis I present a new package for linguistic typology: LingTypology. The package is a Python counterpart of the R package of the same name. It allows to access multiple online linguistic databases and create linguistic interactive maps. Both features of the package may be of use for typological studies. Databases API increases productivity of typological research allowing researchers to access massive amount of data automatically. Also, it simplifies reproduction of linguistic studies. To demonstrate the functionality of LingTypology, I included several typological studies made with the package. The first research reproduces some conclusions of Everett’s article about ejectives and high elevation on the data from the PHOIBLE datasets and reaches the same conclusion: share of languages with ejective consonants is higher in high elevation areas. Also, I performed two small quantitative studies on PHOIBLE, Autotyp and WALS databases to demonstrate the ease of finding correlations that do not have a theoretical background with LingTypology. In the first study, I try to find a correlation with other PHOIBLE features and elevation and Autotyp features and elevation. In the case of PHOIBLE I used chi-square statistical test and in the case of Autotyp I used linear regression. On PHOIBLE data the result was negative while on Autotyp data some regressions had p-value < 0.05. In Autotyp there were several linear regressions that showed p-value < 0.05. In the second study I search for implicative universaliae in WALS. To gain the result I check all pairs of binary features from WALS and calculate chi-square test for each pair. The result is negative. The second feature of LingTypology – interactive maps – can be useful for visualization of typological research. LingTypology package allows to draw linguistic maps with Glottolog data at its core. The map could be rendered as HTML which is useful for implementing it into websites and including into web-publications. The other option is to freeze the map as PNG. It allows to include it into handouts and papers. By default the maps generated are colored. However, LingTypology allows to create black and white maps because some journals does not support color printing.

Full text (added June 4, 2019)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses