September 2023, Recent Advances in Natural Language Processing Conference (RANLP 2023)


RANLP 2023 took place between September 4th-September 6th in Varna, Bulgaria. The research team, represented by Ana-Maria Bucur, Andreea Dinca, Madalina Chitez & Roxana Rogobete, presented the paper entitled “Automatic Extraction of the Romanian Academic Word List: Data and Methods”.

Our study proposes the first empirically based Romanian Academic Word List (Ro-AWL). The paper presents the methodology and data used for the automatic extraction of the RO-AWL. We put forth a methodology for the extraction of the RO-AWL adapted for the Romanian language, which uses the newly compiled Corpus of Expert Writing in Romanian and English (EXPRES) built at CODHUS. Our list can be used to support academic writing teaching activities and NLP tasks focusing on Romanian.

The draft proceedings can be accessed here

Presentation excerpts: