In this project, taggers assigned part-of-speech tags, phrase chunk labels and named-entity labels to the words in sentences. There are 2 models, namely Logistic Regression and Conditional Random Fields for each of the 3 tasks.

There are 2 datasets namely data and data_mini. Initial models use data_mini if you want to use all data uncomment the data directory line in related python scripts main function.

There is a bash script to run all scripts. Also, it saves the output as log file.