Entity Extraction

These docs are for version 1.x of Rasa Open Source. Docs for the new version 2.0 can be found here.

Entity Extraction

Entity extraction involves parsing user messages for required pieces of information. Rasa Open Source provides entity extractors for custom entities as well as pre-trained ones like dates and locations. Here is a summary of the available extractors and what they are used for:

Component Requires Model Notes
CRFEntityExtractor sklearn-crfsuite conditional random field good for training custom entities
SpacyEntityExtractor spaCy averaged perceptron provides pre-trained entities
DucklingHTTPExtractor running duckling context-free grammar provides pre-trained entities
MitieEntityExtractor MITIE structured SVM good for training custom entities
EntitySynonymMapper existing entities N/A maps known synonyms
DIETClassifier conditional random field
on top of a transformer		 good for training custom entities

The “entity” Object

After parsing, an entity is returned as a dictionary. There are two fields that show information about how the pipeline impacted the entities returned: the extractor field of an entity tells you which entity extractor found this particular entity, and the processors field contains the name of components that altered this specific entity.

The use of synonyms can cause the value field not match the text exactly. Instead it will return the trained synonym.

{
  "text": "show me chinese restaurants",
  "intent": "restaurant_search",
  "entities": [
    {
      "start": 8,
      "end": 15,
      "value": "chinese",
      "entity": "cuisine",
      "extractor": "CRFEntityExtractor",
      "confidence": 0.854,
      "processors": []
    }
  ]
}

Note: The confidence will be set by the CRFEntityExtractor component. The DucklingHTTPExtractor will always return 1. The SpacyEntityExtractor extractor and DIETClassifier do not provide this information and return null.

Custom Entities

Almost every chatbot and voice app will have some custom entities. A restaurant assistant should understand chinese as a cuisine, but to a language-learning assistant, it would mean something very different. The CRFEntityExtractor and the DIETClassifier component can learn custom entities in any language, given some training data.

Entities Roles and Groups

Assigning custom entity labels to words allow you to define certain concepts in the data.

For example, we can define what a city is:

I want to fly from [Berlin](city) to [San Francisco](city).

However, sometimes you want to specify entities even further. Let’s assume we want to build an assistant that should book a flight for us. The assistant needs to know which of the two cities in the example above is the departure city and which is the destination city.

- I want to fly from [Berlin]{"entity": "city", "role": "departure"} to [San Francisco]{"entity": "city", "role": "destination"}.

You can also group different entities by specifying a group label next to the entity label.

Give me a [small]{"entity": "size", "group": "1"} pizza with [mushrooms]{"entity": "topping", "group": "1"} and a [large]{"entity": "size", "group": "2"} [pepperoni]{"entity": "topping", "group": "2"}

Extracting Places, Dates, People, Organizations

spaCy has excellent pre-trained named-entity recognizers for a few different languages.

Dates, Amounts of Money, Durations, Distances, Ordinals

The duckling library does a great job of turning expressions like “next Thursday at 8pm” into actual datetime objects that you can use.

Regular Expressions (regex)

You can use regular expressions to help the CRF model learn to recognize entities.

Passing Custom Features to CRFEntityExtractor

If you want to pass custom features, such as pre-trained word embeddings, to CRFEntityExtractor, you can add any dense featurizer to the pipeline before the CRFEntityExtractor.