Chinese Word Sketches

Adam Kilgarriff, Chu-Ren Huang, Pavel Rychly, Simon Smith, 
David Tugwell 

Word sketches are one-page automatic, corpus-based summaries 
of a word's grammatical and collocational behaviour.  They 
were first used in the production of the Macmillan English 
Dictionary (2002).  At that point, they only existed for 
English.  Now, we have developed the Sketch Engine, a corpus 
tool which takes as input a corpus of any language and 
corresponding grammar patterns and which generates word 
sketches for the words of that language.  It also 
automatically generates a thesaurus and 'sketch differences', 
which specify similarities and differences between near-
synonyms. 
We have recently prepared word sketches for Chinese, based 
on the Chinese Gigaword corpus.  The corpus was tokenized 
and part-of-speech tagged in collaboration with Academia 
Sinica.  We shall demonstrate the Chinese word sketches, and 
show how they can be used in lexicography, to enrich and 
improve existing definitions, to quickly add further 
information on collocates, and for selecting typical 
illustrative examples, as well as for more ambitious projects 
involving electronic and web dictionaries and translation aids. 
We shall also describe the software and principles behind it, 
differentiating it from other corpus query systems such as 
Wordsmith and the Stuttgart tools.  We shall outline the issues 
arising in the preparation of the Chinese data.