Work
All projects
ResearchLiveJan 2025 – Jun 2025· PG Main Project — Sole developer

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

0
technologies
0
shipped features
0
decisions logged
huggingface.co/spaces/Nivas007/Tamil_txt_Summarisation_NER
no preview yet

5 sections below

01Overview

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.

02What it does
the parts worth the work
  • 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
03Calls I made
and what each one cost

The section above says what this does. This one says why it is built the way it is — including the parts that did not come free.

  1. Fine-tune with NER wired into trainingoverUse a general-purpose summarisation model as-isPost-process generated summaries to reinsert missing entities
    Because

    Reinserting entities after the fact treats the symptom, not the cause — the model has already learned that dropping names is an acceptable shortcut. Training entity preservation directly into it is what produced the ~30% reduction in information loss over the baseline.

    What it cost

    Every training run needs entity-tagged data, not just raw text-summary pairs — the curated Tamil sports corpus was more expensive to build than for a plain summarisation baseline.

  2. Parameter-efficient fine-tuning (PEFT)overFull fine-tuning of mT5Train a smaller model from scratch for Tamil only
  3. Tamil-specific normalisation and preprocessingoverUse an off-the-shelf multilingual tokenizer unchangedTransliterate Tamil into a Latin-script intermediate form
04Documentation
Tamil Text Summarization using NERdocumentation

// documentation is hidden by default to keep the page light

05Slides
Tamil Text Summarization using NERslide deck

// slide deck is hidden by default to keep the page light

Seen enough?

There are more where this came from — or skip the browsing and just say hello.