Abstract
AbstractThe paper considers the problem of automatic recognition of animacy in the Russian language. We propose a recognizer that is based on the analysis of co-occurrence with the most frequent words and is trained on data from the Russian subcorpus of Google Books Ngram. The obtained recognition accuracy of animacy is 94.3% on the test sample. We also consider the application of the trained recognizer to diachronic data. The performed analysis shows that high recognition accuracy can be obtained even using the data extracted from the corpus for one single year. This allows one, firstly, to diachronically investigate changes in perception of words for which variability of animacy/inanimacy is observed. Secondly, the considered examples show that change in perception of an object as animate or inanimate can serve as a marker of semantic change and, in particular, emergence of new meanings of a word denoting this object. This makes the recognizer a good tool for studies of language evolution.KeywordsAnimacyNeural networksLexical semantics change detectionDiachronic corpus
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
