ThamizhiPOSt is a deep learning based POS tagger which is developed using Stanza framework, and trained using 11K POS tagged sentences along with fasttext model of Facebook. It uses the Universal Dependency POS tagset for the annotation. ThamizhiPOSt shows an F1 score of 93.27 (as of today 02.09.2020) for the TTB ( This is the current state of the art for the Tamil POS taggers which are implemented/reported as of today.
We trained this POS tagger using the AMRITA POS tagged data. Before we do this, we did a harmonisation of BIS, AMRITA and UPOS tagsets, which are the primary POS tagsets available as of today. The harmonisation Universal Dependency POS (UPOS), BIS , and AMRITA can be be found in this sheet . However, we found that the Amrita POS tagged data are more clean, therefore, we used it to train the POS tagger. We used Stanza, a neural based framework developed by Stanford University - a sccuessor of their CoreNLP framework, to train the POS tagger.

The trained models can be found here in a compressed format. This file is in tgz format, you can extract it using tar.

How to use ThamizhiPOSt

1. Download and install Stanza, as outlined here:
2. Donwload trained models, and place them in a folder called models
3. Insert your data to be POS tagged in a file called sentence.txt, and place it in the same level as the models folder
4. Download and place, along with sentence.txt
5. Execute the python script -, output will be written to a file called pos-tagged-sentence.txt

Note: In this version of tagger, it is compulsory to include a symbol (can be a period/exclamation mark / question mark) at the end of each line/sentence. Otherwise, the very last token will be considered as a punctuation.

An output will look like the following for the data "தமிழ் எங்கள் உயிருக்கு நேர் ."
1 தமிழ் PROPN
2 எங்கள் PRON
3 உயிருக்கு NOUN
4 நேர் NOUN


This research was supported by the Accelerating Higher Education Expansion and Development (AHEAD) Operation of the Ministry of Higher Education, Sri Lanka funded by the World Bank.