Chris Pollett > Students >

    ( Print View)



    [CS 297 Proposal]





    [CS297 Report-PDF]

    [CS 298 Proposal]

    [CS298 Report-PDF]

    [CS298 slides-PDF]

Implemented a Chinese POS tagging for Yioop to tag segmented sentence


This is the project related to Chinese NLP. In the implementation, the tagger should be trained with data before being used. The main idea of the implementation is to use the statistic of the words POS and the words(features) around it.

I use the viterbi algorithm to find out the most likely POS of the word.

The result has an accuracy (I will figure out this later).

Currently the weight of the features are hard coded. In the future work, this weight should be trained or adjusted to have a better result.


Chinese POS tagging