NewsSum V2 Demo

NewsSum V2 Demo

Compares two news summarizers side by side in your browser, a length-matched TextRank and a BART-base model fine-tuned on BBC news, for people studying summarization.

Made by MHkhan50 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: NewsSum V2 Demo is a browser page that sets two news summarizers next to each other. One is a TextRank summarizer matched to the same length. The other is BART-base fine-tuned on the BBC News Summary data. The metadata names the model MHkhan50/newssum-bart-base-bbc.

Who it suits: People who study text summarization and want to see an extractive method and a fine-tuned model compared on news.

Industry | Who uses it | How they use it | Example
NLP research | Researchers | Compare an extractive and a fine-tuned summarizer | Reading both summaries of one article
Education | Students of language models | See what fine-tuning changes in a summary | Putting a TextRank summary beside a BART one
Media | Editors curious about automatic summaries | Judge how two methods handle news text | Checking which summary reads better

If you need to summarize documents that are not news, you can skip it, because the demo is built around BBC news.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• A browser on Windows, macOS or Linux, by opening a downloaded copy of index.html

Use case | Who | What they get back
Compare two summarizers | Researchers | Two summaries shown side by side
Teach summarization | Teachers | A visible example of extractive and fine-tuned output
Study a browser demo | Developers | A small static page with HTML and a style sheet

How to set it up: Online, nothing needs installing. A local copy needs a browser and a little Python for the download.

• A web browser
• Python and the pip tool, only for the download step

1. Install the Hugging Face hub package with pip.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Open index.html in a web browser.

pip install -U huggingface_hub
hf download MHkhan50/newssum-demo --repo-type space --local-dir newssum-demo
cd newssum-demo

How to use it: Open the Space's page, or index.html from a local copy, and read the two summaries it shows side by side. The source lists no other controls, so the labels on the page are your guide.

hf download MHkhan50/newssum-demo --repo-type space --local-dir newssum-demo

Example: You open the page and read the TextRank summary and the BART summary of a news story next to each other. You then decide which one keeps the key facts better. The source shows no sample output, so the exact layout is not described here.

For newcomers and experts: A summarizer shortens a long text. TextRank picks the most central sentences from the original, while BART writes new sentences. To start, open the page and read the two results one after the other.

The TextRank side is length-matched, so the two summaries are about the same size and the comparison is fair. The BART side was tuned on BBC News Summary, a news dataset, so it knows news writing. The source gives no scores here and points to a separate repository for results.

Open the page in a browser
A news text goes to both summarizers
TextRank and BART produce summaries
You compare them side by side

Good to know:

• License: MIT
• Cost to run: none named
• Data it reaches: the news text you give it, and the fine-tuned model named in its metadata
• Not for: the source names no forbidden uses

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: static
• License: mit

Links

• Space: https://huggingface.co/spaces/MHkhan50/newssum-demo
• Files: https://huggingface.co/spaces/MHkhan50/newssum-demo/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.