User:Doldham1/Final project

From LING073
< User:Doldham1
Revision as of 22:39, 12 May 2017 by Doldham1 (talk | contribs) (Transducer)

Jump to: navigation, search

Project Details

What I did

Corpus

Transducer

  • I implemented numbers by having a digits lexicon which goes in a loop, and then adds various forms like year, day, and hour to the end of a number.
  • I wrote four twol rules to handle the conjugations of u verbs for た、て、and ない forms.

What I did not do

  • Tokenisation
  • Prefixes (e.g. 毎 for every, お and ご for honorific, etc.)

Repositories

Transducer

Corpus

Evaluation

  • Coverage over the Hiroshima article:
  • Coverage over the grapefruit article:
  • Coverage over the shibori article:
  • Coverage over the orc article:
  • Coverage over all articles:

Precision and recall would also be useful metrics, but I did not have time to work on them.