← Back to catalogue
Research draft

natural language processing

vr.tr.natural-language-processing · INF.KNW

Let an agent explain natural language processing and its tasks and methods, describe applications and limitations, support learning and project planning, and present debates about bias, evaluation and impact with attribution.

Thing Registry Information and virtual systems

Research draft, second pass

A second pass drafted this model: the structure a model of this thing needs, and what is known about it in the world. The line under this one says how the second half was obtained - researched against sources, or recalled without web access, in which case nothing here was read anywhere and every claim is a lead to verify. Unreviewed either way.

written by Claude from model knowledge without web access - no source was read, every claim is a lead to verify

Researched by: Claude

Purpose and description

Let an agent explain natural language processing and its tasks and methods, describe applications and limitations, support learning and project planning, and present debates about bias, evaluation and impact with attribution.

A field of artificial intelligence and computational linguistics concerned with enabling computers to process, understand and generate human language, covering tasks such as syntactic parsing, natural language understanding, machine translation, speech recognition and speaker verification, dialogue systems, information extraction and entity linking, and large language models; natural language processing draws on linguistics, statistics and machine learning and underlies search, assistants, translation and text analytics.

What it is for: Computational processing of human language.

It can be explain tasks and methods; describe applications and limits; support learning and planning; present debates.

Distinguishing features

Language tasks

Statistical and neural methods

Wide applications

Evaluation benchmarks

What it looks like

Not physical; software and models.

How it is recognised

Computers processing human language

Parsing, understanding, generation, speech

Linguistics studies language itself; computer vision processes images

Related models

is a kind of - category

artificial intelligence

is a kind of - category

computational linguistics

is related to - context in language models

context

is related to - meaning and signs

semiotics

In practice

Families and kinds

syntactic and semantic analysis

machine translation

speech recognition and synthesis

dialogue systems and assistants

information extraction and language models

Standards and regulation

Evaluation benchmarks and shared tasks

Data protection rules for language data

Artificial intelligence regulation

Failure modes and hazards

Bias and errors in models

Overclaiming understanding

Privacy risks in language data

Also called

dialogue systemAudreyWikificationspeaker verificationnatural language understandingsyntactic parsingMāori natural language processingstatistical natural language processingmachine reading comprehensionpart-of-speech taggingChinese character processingautomatic summarizationsemantic clusteringinformation extractionspeech recognitionmorphological analysistext segmentationsentiment analysistokenizationChinese information processingsentence embeddingtext simplificationcomputer-based question classificationbiomedical natural language processingtext miningSemantic analysissemantic role labelingMorphological parsingknowledge-intensive natural language understandingnatural language inferencetable extractionevent detectionNoisy text analyticsterminology extractionopen information extractionword segmentationdecompoundingsarcasm recognitionMultimodal sentiment analysistopic detection and tracking

+7

Where this came from

wikidata · CC0 1.0

Source repository Registry entry point

Also registered as vr.tr.natural-language-processing

Drafted structure

Bundle to layer to finding to question, as the second pass will find it: 4 bundles · 8 layers · 8 findings · 16 questions.

Understand What natural language processing is.

Computing.

Tasks

Tasks.

Tasks

Tasks.

  1. What are the main tasks of natural language processing, from parsing and understanding to translation, speech and dialogue? definition
  2. Which task is meant? boundary

Methods

Methods.

Methods

Methods.

  1. How have rule-based, statistical and neural methods, including language models, approached these tasks? provenance
  2. Which entry fits machine learning? action
Build Building systems.

Practice.

Plan

Planning a project.

Plan

Planning.

  1. How can a language processing project be scoped, with data, models and evaluation? action
  2. Which entry fits a specific toolkit? action

Evaluate

Evaluation.

Evaluate

Evaluation.

  1. How are systems evaluated, and what are the limits of benchmarks? provenance
  2. Which findings are contested? boundary
Apply Applications and issues.

Attribution.

Applications

Applications.

Applications

Applications.

  1. How is natural language processing used in search, assistants, translation, health and business? provenance
  2. Which entry fits a specific application? action

Issues

Bias, privacy and impact.

Issues

Issues.

  1. What issues of bias, privacy, misinformation and labour impact arise, with positions attributed? provenance
  2. Is the presentation neutral? boundary
Learn History and teaching.

Education.

History

History.

History

History.

  1. How did the field develop from early machine translation and dialogue systems to neural models? provenance
  2. Which references are standard? provenance

Teach

Teaching.

Teach

Teaching.

  1. How can natural language processing be taught? action
  2. Which misconceptions arise? provenance

What the second pass must settle

  • Should large language models be a separate entry?
  • How should benchmarks be linked?
  • How should regulation be linked?
Draft as JSON