Open dwhieb opened 3 years ago
This could be achieved by the English phrase analyzer transcriptor that we already have, e.g.
flookup -b -i -x transcriptor-eng-phrase2crk-features.fomabin
he sees `him`
sees +V+TA+3Sg+3SgO
he sees it
sees +V+TI+3Sg+0SgO
he sees
sees +V+AI+3Sg
it is green
is green +V+II+0Sg
there is rain
is rain +V+II+0Sg
it rains
rains +V+II+0Sg
The FST source can be found here: https://github.com/giellalt/lang-crk/blob/develop/src/transcriptions/transcriptor-eng-phrase2crk-features.xfscript
Write a script that accepts a normalized English definition (see #21) and attempts to guess the inflectional class of the associated Cree word.
If using the FST, this is probably easiest done as a preprocessing step for MD, after normalizing the definition, but before the aggregation step.