Quantitative answers to qualitative questions? Combining linguistic layers in corpus data
Word classes as a concept goes back to antique, and despite the problems related to this category, it still belongs to the central ones in theoretical linguistics. When analysing large amounts of linguistic data, we cannot manage without specification of parts of speech.
In the workshop we would like to discuss topics related to the role of PoSs in corpus analysis and other digital tools processing language. How do languages differ in respect to the PoS role in corpus analysis? What kinds of problems arise in connection with PoSs when creating automatic systems? As PoSs combine syntactic, morphological and semantic information, what would be the best way to unite these levels for the best possible outcome when dealing with the PoSs in corpus analysis and lexicographic work?
The working language is English.
(to be announced)
Date: 22 April, 2020
Venue: (to be announced)
Kontakt / Contact
Geda Paulsen (Institute of the Estonian Language), geda.paulsen[at]eki.ee
► Registreerimine konverentsile / Registration to the Conference (avaneb veebruaris / to be opened in February)
Center of Estonian Language Resources, Institute of the Estonian Language