Tasks

Summarization

Summarization is the task of producing a shorter version of a document while preserving its important information. Some models can extract text from the original input, while other models can generate entirely new text.

Inputs
Input

The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. It was the first structure to reach a height of 300 metres. Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.

Summarization Model
Output
Output

The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building. It was the first structure to reach a height of 300 metres.

About Summarization

Use Cases

Research Paper Summarization 🧐

Research papers can be summarized to allow researchers to spend less time selecting which articles to read. There are several approaches you can take for a task like this:

  1. Use an existing extractive summarization model on the Hub to do inference.
  2. Pick an existing language model trained for academic papers. This model can then be trained in a process called fine-tuning so it can solve the summarization task.
  3. Use a sequence-to-sequence model like T5 for abstractive text summarization.

Inference

You can use the πŸ€— Transformers library summarization pipeline to infer with existing Summarization models. If no model name is provided the pipeline will be initialized with sshleifer/distilbart-cnn-12-6.

from transformers import pipeline

classifier = pipeline("summarization")
classifier("Paris is the capital and most populous city of France, with an estimated population of 2,175,601 residents as of 2018, in an area of more than 105 square kilometres (41 square miles). The City of Paris is the centre and seat of government of the region and province of Île-de-France, or Paris Region, which has an estimated population of 12,174,880, or about 18 percent of the population of France as of 2017.")
## [{ "summary_text": " Paris is the capital and most populous city of France..." }]

You can use Model Database.js to infer summarization models on Model Database Hub.

import { HfInference } from "@Model Database/inference";

const inference = new HfInference(HF_ACCESS_TOKEN);
const inputs = "Paris is the capital and most populous city of France, with an estimated population of 2,175,601 residents as of 2018, in an area of more than 105 square kilometres (41 square miles). The City of Paris is the centre and seat of government of the region and province of Île-de-France, or Paris Region, which has an estimated population of 12,174,880, or about 18 percent of the population of France as of 2017."

await inference.summarization({
  model: 'sshleifer/distilbart-cnn-12-6',
  inputs
})

Useful Resources

Would you like to learn more about the topic? Awesome! Here you can find some curated resources that you may find helpful!

Notebooks

Scripts for training

Documentation

Compatible libraries

Summarization demo
Summarization
Examples
This model can be loaded on the Inference API on-demand.
Models for Summarization
Browse Models (1,303)

Note A strong summarization model trained on English news articles. Excels at generating factual summaries.

Datasets for Summarization
Browse Datasets (475)

Note News articles in five different languages along with their summaries. Widely used for benchmarking multilingual summarization models.

Note English conversations and their summaries. Useful for benchmarking conversational agents.

Spaces using Summarization

Note An application that can summarize long paragraphs.

Note A much needed summarization application for terms and conditions.

Note An application that summarizes long documents.

Note An application that can detect errors in abstractive summarization.

Metrics for Summarization
rouge
The generated sequence is compared against its summary, and the overlap of tokens are counted. ROUGE-N refers to overlap of N subsequent tokens, ROUGE-1 refers to overlap of single tokens and ROUGE-2 is the overlap of two subsequent tokens.