Pregled bibliografske jedinice broj: 641112
Natural Language Processing in Philological Research
Natural Language Processing in Philological Research // The Study of Asia: between Antiquity and Modernity / Keidan, Artemij (ur.).
Cagliari: Coffee Break Project, 2012. str. 32-34 (predavanje, nije recenziran, sažetak, ostalo)
CROSBI ID: 641112 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Natural Language Processing in Philological Research
Autori
Štefanec, Vanja
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, ostalo
Izvornik
The Study of Asia: between Antiquity and Modernity
/ Keidan, Artemij - Cagliari : Coffee Break Project, 2012, 32-34
ISBN
978-1-4716-9248-2
Skup
Coffee Break Conference III
Mjesto i datum
Cagliari, Italija, 13.06.2012. - 16.06.2012
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Nije recenziran
Ključne riječi
natural language processing; automatic text processing; philology; indology
Sažetak
The use of quantitative methodology is not a novelty in philological research. The information about the frequency of certain linguistic units or textual patterns and their distribution within a text or corpus has proven to be very useful by many scientists working with text. That information can be a very convincing argument when dealing with various questions which philologists often have to address, such as dating of the text, identifying textual layers, determining the authorship, determining the relation between different texts, composition strategies, etc. Nowadays, by using a digital computer, it is possible to perform not just simple text processing, but also very complex language analyses on all linguistic levels (phonological, morphological, syntactic and semantic), while the required linguistic knowledge is formalized and stored in a computational model. The most common output of such analyses is the annotated text, i.e. text furnished with linguistic annotations that can be easily searched and subdued to statistical and distributional analysis. In this paper we will show some state-of-the-art techniques and tools for natural language processing with a special emphasis on their application in philological research. We will explain how these tools are used on the example of the Indian epic Rāmāyaṇa and also describe how available resources can be used and employed in our own research.
Izvorni jezik
Engleski
Znanstvena područja
Informacijske i komunikacijske znanosti, Filologija