Natural Language Processing

← Back to Domain-Specific Abstractions by Domain

7 domain-specific abstractions whose origin domain is Natural Language Processing.

• Bag-of-words model — A text representation that records which tokens occur and often their counts or weights while discarding word order and most grammatical structure.
• Logic form — A shallow first-order knowledge representation that maps natural-language content into conjoined predicates connected by shared event and entity variables, optionally decorated with word senses.
• Morphological parsing — Analysis of a word into morphemes together with their lexical identities, grammatical features, and combinatorial structure.
• Relationship extraction — An information-extraction task that detects entity pairs or other arguments in artifacts and assigns the semantic relation expressed between them.
• Semantic compression — Lossy reduction of lexical diversity by replacing expressions with a smaller concept vocabulary while attempting to preserve their meaning.
• Semantic parsing — The computational task of mapping a natural-language utterance into a machine-interpretable formal meaning representation that supports execution, inference or structured comparison.
• Word embedding — A learned vector representation of words or tokens in which geometric relations encode patterns of distributional or task-specific similarity.