Enriching Linguistic Representation in the Cantonese Wordnet and Building the New Cantonese Wordnet Corpus

This paper reports on the most recent improvements on the Cantonese Wordnet, a wordnet project started in 2019 (Sio and Morgado da Costa, 2019) with the aim of capturing and organizing lexico-semantic information of Hong Kong Cantonese. The improvements we present here extend both the breadth and depth of the Cantonese Wordnet: increasing the general coverage, adding functional categories, enriching verbal representations, as well as creating the Cantonese Wordnet Corpus - a corpus of handcrafted examples where individual senses are shown in context.