ResearchJan 2025 – Jun 2025· PG Main Project — Sole developer

Tamil Text Summarization using NER

Research-level NLP system that summarizes Tamil sports news while preserving key named entities.

Go to the site

no public repository for this project

// stack

import Python from 'tamil-ner-summarizer'

import NLTK from 'tamil-ner-summarizer'

import SpaCy from 'tamil-ner-summarizer'

import TensorFlow from 'tamil-ner-summarizer'

import Deep Learning from 'tamil-ner-summarizer'

import NER from 'tamil-ner-summarizer'

import Streamlit from 'tamil-ner-summarizer'

import Hugging Face Transformers from 'tamil-ner-summarizer'

import mT5 from 'tamil-ner-summarizer'

import PEFT from 'tamil-ner-summarizer'

// overview

A Tamil sports news summarization system combining Named Entity Recognition with abstractive deep learning. The model preserves critical entities — players, scores, locations — that generic summarizers routinely drop, reducing information loss by roughly 30% against the baseline. Built as my postgraduate main project at Pondicherry University and deployed as a live Hugging Face Space.

// highlights

▹Combined NER with abstractive deep learning to preserve players, scores and locations in generated summaries
▹Reduced information loss by ~30% compared to the baseline summarizer
▹Solved low-resource language challenges: Tamil-specific tokenization, normalization and preprocessing
▹Trained and evaluated on a curated Tamil sports news corpus
▹Live Hugging Face Space demo

// screenshots

Tamil Text Summarization using NER screenshot 1

01 / 01open full size ↗