Digital Perspectives for Corpus Processing of Texts Written in Armenian
In collaboration with the GREgORI project, Calfa will present a full pipeline for document analysis in Armenian (from scans to analyzed texts).
Armenian through the Ages — Linguistic and Philological Perspectives
The Faculty of Linguistics, Philology and Phonetics at the University of Oxford, in association with Wolfson College, will hold a conference entitled “Armenian through the Ages: Linguistic and Philological Perspectives” at Wolfson College, Oxford, on 22 January 2021. Due to COVID, the conference will take place on Friday, 22 January 2021, via Zoom.
GREgORI Project and Calfa will jointly introduce a new modus operandi to allow the semi-automatic construction of annotated corpora. In practice, will be described a chain of programs enabling complete processing of texts, from their automated input (by Handwritten Text Recognition for manuscripts; by OCR for printed texts), to their lemmatization (lemma, grammatical category, morphological analysis). In the end, produced annotated corpora can be displayed on dedicated interfaces.
See conference program and abstracts here.
In particular, Calfa will present its new Vision interface (Assisted and automated transcription interface) and GREgORI its last achievments in corpora display.