The English-to-Kazakh chunker As regards the first round of structural transfer (the “chunker”, rules written in the apertium-eng-
kaz.eng-kaz.t1x file), rules have been written to address some of the the main local morphosyntactic
divergences between the languages involved. The prototype is able to perform the local operations
necessary to adequately process short noun phrases, adjective phrases, verb phrases and
adpositional phrases (that is, prepositional phrases in English and postpositional phrases in
Kazakh).
Chunking rules, of which there are currently 60, identify six kinds of chunks and translate them
into Kazakh as much as possible, leaving some minor operations to be performed in later stages of
structural transfer (for instance, the case of noun phrases). Table Table shows a description of the
kinds of chunks found, with examples, and the chunk-level tags associated to them. The translation
of English noun phrases and prepositional phrases are given below as examples.
Table 2: Chunk-level tags currently associated to each type of chunk. Those marked with an
asterisk correspond to optional morphemes that will need special treatment in a cleanup module (see
text in section 0).
