Complementizers - Complementizers are words that mark an embedded clause, especially a clause functioning as the complement of another expression.
Componential analysis - Componential analysis is an approach to word meaning that describes lexical items through smaller semantic features or components.
Computational linguistics - Computational linguistics is the study of human language using computational models and methods.
Computational semantics - Definition: Computational semantics studies how computers can represent and process linguistic meaning.
Concept mining - Definition: Concept mining is the computational identification of meaningful concepts in material such as documents, queries or other data.
Conceptual dependency - Conceptual dependency is a historical approach to representing the meaning of language through networks of concepts, primitive acts and their participants.
Concrete word - A concrete word is a word whose meaning is closely connected to something perceptible through the senses or to a directly experienced action.
Conditional generation - Conditional generation is the production of an output using specified input or context as a condition.
Connotation frame - A connotation frame is a structured representation of the attitudes and other implications a predicate can convey about its participants.
Connotations - Connotations are the associations, evaluations or emotional overtones carried by a word or expression beyond its basic descriptive meaning.
Consonant - A consonant is a speech sound typically produced with a narrowing or closure somewhere in the vocal tract.
Constative speech act - A constative speech act presents something as being the case, committing the speaker to a proposition in the relevant conversational sense.
Constituency - Constituency is the organization of a sentence into groups of words that function as grammatical units.
Constraint Grammar - Constraint Grammar is a rule-based framework for analyzing text by using contextual constraints to remove or select among possible linguistic readings.
Content determination - Definition: Content determination is the natural language generation task of deciding what information a generated text should communicate.
Content words - Content words are words whose main contribution is lexical meaning: the people, things, actions, properties and circumstances a message describes.
Context-free grammar - A context-free grammar, or CFG, is a formal system of rules for building strings and describing their hierarchical structure.
Context window - A context window is the limited amount of information a language model can work with in a particular generation.
Continuation rise - A continuation rise is an intonation pattern in which pitch rises near a phrase boundary in a way associated with more material to come.
Continuer - A continuer is a short listener response that acknowledges an ongoing contribution and allows or encourages the speaker to carry on.
Contrastive search - Contrastive search is a text-decoding method that selects a next token by balancing its model probability against its hidden-state similarity to previous...
Controlled natural language - Definition: A controlled natural language is a deliberately designed form of a natural language with specified restrictions on vocabulary, grammar or...
Conversation analysis - Conversation analysis is the systematic study of how people organize social interaction through successive contributions.
Conversational speech - Conversational speech is speech produced as people interact, typically with contributions shaped by what others say and do.
Conversational user interface - Definition: A conversational user interface lets people interact with software through exchanges resembling conversation, using written language, speech or...
Coordination ambiguity - Coordination ambiguity arises when an expression containing a conjunction, such as and or or, allows more than one structural grouping.
Copula - A copula is a linking element that connects a subject with a predicate expressing a property, classification, identity or related state.
Coreference chain - A coreference chain is a set of expressions in a discourse that refer to the same entity. It can connect a name, a description and a pronoun across sentences.
Coreference resolution - Coreference resolution is the task of determining which expressions in a discourse refer to the same entity.
Coronal sound - A coronal sound is a speech sound articulated using the tongue tip or blade as the principal active articulator for its constriction.
Count nouns - Count nouns are nouns used to present their referents as distinct units that can be counted.
Counters - In the language context of this glossary, counters are counting expressions used with numerals to indicate the kind or unit of what is being counted.
Cross-brackets - Cross-brackets, or crossing brackets, are a constituency-parser evaluation measure of incompatible phrase boundaries between a predicted parse and a...
Cross-language information retrieval - Definition: Cross-language information retrieval, or CLIR, searches for relevant information written in a language different from the query language.
DAMSL - DAMSL stands for Dialog Act Markup in Several Layers.
Data contamination - Data contamination, in model evaluation, occurs when material meant to provide an independent test has entered the model's training or development process...
Datasheet - A datasheet for a dataset is structured documentation explaining why a dataset was created, what it contains, how it was collected and prepared, how it...
Dative alternation - The dative alternation is a choice between related grammatical constructions for expressing a recipient and a transferred theme.
De-skilling - De-skilling is the reduction or loss of a person's ability to perform a task, or the redesign of work so that less expertise is required or exercised.
Decoding - Decoding is the inference process that turns a model's scores or probabilities into a selected output sequence.
Deep learning speech synthesis - Definition: Deep learning speech synthesis uses neural networks with multiple processing layers to generate speech audio.
Deep linguistic processing - Definition: Deep linguistic processing analyses language using detailed grammatical and semantic structure.
Definite reference - Definite reference is a use of language that presents an intended referent as identifiable to the listener or reader in the relevant context.
Degree adverb - A degree adverb expresses the extent, intensity or sufficiency of a property, state or activity.
Dental sound - A dental sound is a speech sound whose principal constriction involves the tongue at the teeth.
Dependency tree - A dependency tree represents the syntactic structure of a sentence through directed relations between its words.
Derivational morphemes - Derivational morphemes are meaningful word-building units that help form new lexical words from a base. They can change meaning, grammatical category or both.
Determiner - A determiner is a grammatical word associated with a noun phrase that helps express how its referent should be understood in context.