Abstractive Document Summarization

Formulate natural language summaries of text documents. Submit a text document (will be truncated at ~800 words), and receive back a summary of ~200 words.

Apply for access Private documentation

Intended use

Problem types:

Generating natural language summaries for various types of text documents. The model can be applied to a wide range of documents, including news articles, scientific publications, legal documents, emails, etc.

Inputs and outputs:

  • Users provide: text document (will be truncated to the first ~700-800 words)
  • Users receive: text summary (maximum length of ~200 words)

Industries and functions:

Customers who are interested to generate natural language summaries of their business documents, emails, reports or any other type of a text document.

Technical challenges:

  • Input text documents will be truncated to the first ~700-800 words due to performance limitations. Users need to ensure that the most relevant information they want to summarize is within that range.
  • While the models have been trained on a diverse range of text domains, it will be challenging to adapt to new unseen domains without re-training the models.

What data do I need?

Data and label types:

Submit a text document to this API, and receive back a text summary of the document.

What skills do I need?

As with all AI Workshop experiments, successful users are likely to be savvy with core AI concepts and skills in order to both deploy the experiment technology and interact with our AI researchers and engineers.

In particular, users of this experiment should:

  • Be familiar with accessing Google APIs