Building the Cantonese Wordnet

Code

• github.com/lmorgadodacosta/cantonesewn
  OfficialIn papernone★ 14

Abstract

This paper reports on the development of the Cantonese Wordnet, a new wordnet project based on Hong Kong Cantonese. It is built using the expansion approach, leveraging on the existing Chinese Open Wordnet, and the Princeton Wordnet’s semantic hierarchy. The main goal of our project was to produce a high quality, human-curated resource – and this paper reports on the initial efforts and steady progress of our building method. It is our belief that the lexical data made available by this wordnet, including Jyutping romanization, will be useful for a variety of future uses, including many language processing tasks and linguistic research on Cantonese and its interactions with other Chinese dialects.

Reproductions