Noun phrase extraction

The Watson Natural Language Processing Noun phrase extraction block extracts noun phrases from input text.

Block name

noun-phrases_rbr_<language>_stock

Note: The "rbr" abbreviation in model name means rule-based reasoning. RBR models handle syntactically regular entity types such as number, email and phone.

Supported languages

Noun phrase extraction is available for the following languages. For a list of the language codes and the corresponding language, see Language codes.

ar, cs, da, de, es, en, fi, fr, he, hi, it, ja, ko, nb, nl, nn, pt, ro, ru, sk, sv, tr, zh_cn, zh_tw

Capabilities

The Noun phrase extraction block extracts non-overlapping noun phrases from the input text.

Capabilities of noun phrase extraction based on an example
Capabilities Examples
Extraction of non-overlapping noun phrases "Anna went to school at University of California Santa Cruz" -> Anna, school, University of California Santa Cruz

Dependencies on other blocks

None

Code sample

import watson_nlp

# Load the model for English
noun_phrases_model = watson_nlp.load('noun-phrases_rbr_en_stock')

# Run the model on the input text
noun_phrases = noun_phrases_model.run('Anna went to school at University of California Santa Cruz')
print(noun_phrases)

Output of the code sample:

{
  "noun_phrases": [
    {
      "span": {
        "begin": 0,
        "end": 4,
        "text": "Anna"
      }
    },
    {
      "span": {
        "begin": 13,
        "end": 19,
        "text": "school"
      }
    },
    {
      "span": {
        "begin": 23,
        "end": 58,
        "text": "University of California Santa Cruz"
      }
    }
  ],
  "producer_id": {
    "name": "RBR Noun phrases",
    "version": "0.0.1"
  }
}

Parent topic: Watson Natural Language Processing task catalog