Skip to main content
This assignment is due before 11:59AM on Wednesday, October 9, 2024.

POS with Trigram HMM : Assignment 2

In this project, you will implement several approaches for part-of-speech (POS) tagging. Unlike the classification and regression tasks of the first two assignments, POS tagging requires generation of an entire sequence of predicted values, the parts of speech corresponding to each word. To build your POS tagger, you will use data from the Penn Treebank that includes POS tagged sentences. After you have built your POS taggers, run them on the sentences in the test set, and submit your best POS tag predictions to the leaderboard.

Please see the full description of the project attached below.

Here are the materials that you should download for this assignment:

Deliverables

Here are the deliverables that you will need to submit:

  • Code, as always, in Python 3.
  • Predictions on the test set ( Note we limit to 5 submission per day )
  • PDF Report (called writeup.pdf)