ESA Semantic Relatedness

Welcome to the ESA Semantic Relatedness API. This implementation is based on Explicit Semantic Analysis which describes a method for calculating semantic similarities between linguistic items based on their distributional semantic properties over Wikipedia. Distributional semantic models such as ESA are based on the Distributional Hypothesis, which states that words co-occurring in similar contexts tend to have similar meaning.

For further information, please visit us at amtera.solutions.

Using the API

To use the API you must:

• append the language code to the endpoint URL:

    /relatedness/en

• provide a JSON payload with the following structure:

    {
      "t1": "Chris Froome wins Tour de France",
      "t2": "Wikinews interviews Spanish Paralympic track and field athlete David Casinos"
    }

or

    {
      "t1": "Chris Froome wins Tour de France",
      "t2": "Queensland government not doing enough on water: Poll"
    }

Each text must be 120 char. max.

• get the results:

    {
      "t1": "Chris Froome wins Tour de France",
      "t2": "Wikinews interviews Spanish Paralympic track and field athlete David Casinos",
      "v": 0.0038747663
    }

or

    {
      "t1": "Chris Froome wins Tour de France",
      "t2": "Queensland government not doing enough on water: Poll",
      "v": 0.0007662044
    }

showing that the first pair of texts is closer in meaning than the second one.

Billing

You will be charged based on the number of compared pairs. Currently, it’s only possible to submit one pair per request, but this may not be the case in the future.