Skip to content

Enum: NLPComponentType

Components of a natural-language-processing pipeline as enumerated in Clauses 3.6 and 9.2.

URI: iso22989:NLPComponentType

Permissible Values

Value Meaning Description
tokenisation None Segmenting text into tokens such as words or subwords
lemmatisation None Reducing tokens to their canonical dictionary form
part_of_speech_tagging None Assigning grammatical category labels to tokens
syntactic_parsing None Producing syntactic structure for sentences
semantic_analysis None Deriving meaning representations from text
named_entity_recognition None Identifying and classifying named entities in text
sentiment_analysis None Estimating subjective polarity or affect in text
machine_translation None Automatically translating text between natural languages
speech_recognition None Converting acoustic speech signals into text
speech_synthesis None Generating speech audio from text
natural_language_understanding None Deriving structured meaning, intent or entities from natural-language input (...
natural_language_generation None Producing natural-language output from structured inputs (Clause 9
automatic_summarization None Producing condensed summaries of longer text (Clause 3
dialogue_management None Controlling multi-turn conversational interaction (Clause 9
information_retrieval None Finding relevant documents or passages in a collection in response to a query
question_answering None Producing direct answers to natural-language questions
relationship_extraction None Identifying typed relationships between entities mentioned in text
emotion_recognition None Detecting affective or emotional state expressed in text or speech
optical_character_recognition None Converting images of printed or handwritten text into machine-readable text (...
coreference_resolution None Linking mentions in text that refer to the same entity

Slots

Name Description
nlp_component_type Type of NLP pipeline component (Clause 9

In Subsets

Identifier and Mapping Information

Schema Source

LinkML Source

name: NLPComponentType
description: Components of a natural-language-processing pipeline as enumerated in
  Clauses 3.6 and 9.2.
in_subset:
- terminology
from_schema: https://w3id.org/lmodel/iso22989
rank: 1000
permissible_values:
  tokenisation:
    text: tokenisation
    description: Segmenting text into tokens such as words or subwords.
  lemmatisation:
    text: lemmatisation
    description: Reducing tokens to their canonical dictionary form.
  part_of_speech_tagging:
    text: part_of_speech_tagging
    description: Assigning grammatical category labels to tokens.
  syntactic_parsing:
    text: syntactic_parsing
    description: Producing syntactic structure for sentences.
  semantic_analysis:
    text: semantic_analysis
    description: Deriving meaning representations from text.
  named_entity_recognition:
    text: named_entity_recognition
    description: Identifying and classifying named entities in text.
  sentiment_analysis:
    text: sentiment_analysis
    description: Estimating subjective polarity or affect in text.
  machine_translation:
    text: machine_translation
    description: Automatically translating text between natural languages.
  speech_recognition:
    text: speech_recognition
    description: Converting acoustic speech signals into text.
  speech_synthesis:
    text: speech_synthesis
    description: Generating speech audio from text.
  natural_language_understanding:
    text: natural_language_understanding
    description: Deriving structured meaning, intent or entities from natural-language
      input (Clause 9.2).
  natural_language_generation:
    text: natural_language_generation
    description: Producing natural-language output from structured inputs (Clause
      9.2).
  automatic_summarization:
    text: automatic_summarization
    description: Producing condensed summaries of longer text (Clause 3.6.1).
  dialogue_management:
    text: dialogue_management
    description: Controlling multi-turn conversational interaction (Clause 9.2.2).
  information_retrieval:
    text: information_retrieval
    description: Finding relevant documents or passages in a collection in response
      to a query.
  question_answering:
    text: question_answering
    description: Producing direct answers to natural-language questions.
  relationship_extraction:
    text: relationship_extraction
    description: Identifying typed relationships between entities mentioned in text.
  emotion_recognition:
    text: emotion_recognition
    description: Detecting affective or emotional state expressed in text or speech.
  optical_character_recognition:
    text: optical_character_recognition
    description: Converting images of printed or handwritten text into machine-readable
      text (Clause 3.6.12).
  coreference_resolution:
    text: coreference_resolution
    description: Linking mentions in text that refer to the same entity.