Automatic acquisition of lexicon - Definition: Automatic acquisition of a lexicon is the computational construction or expansion of structured lexical entries from language data.
Automatic taxonomy construction - Definition: Automatic taxonomy construction uses computational methods to build or expand a hierarchy of concepts from text or other evidence.
Auxiliary - An auxiliary is a grammatical word that helps express distinctions such as tense, aspect, voice, or modality in a predicate.
Backoff - Backoff is a language-modeling strategy that uses a less specific estimate when the more specific context lacks sufficient evidence.
Backtranslation - Backtranslation is a machine-translation training technique that turns target-language text into additional synthetic parallel data.
Backus-Naur form - Backus-Naur form, or BNF, is a notation for specifying a context-free grammar.
Basic emotions - Basic emotions are a limited set of emotion categories proposed as fundamental within a particular theory of emotion.
Beam width - Beam width is the maximum number of candidate partial solutions retained at a step of a beam-search procedure.
Benchmarks - Benchmarks are specified tasks, data and evaluation procedures used to compare systems under shared conditions.
Best-worst scaling - Best-worst scaling is a comparative annotation method in which a person selects the highest and lowest items on a specified property from a small group.
Bilabial - Bilabial describes a speech sound whose primary constriction is made using both lips.
Binary branching - Binary branching describes a tree structure in which a branching node has two immediate children.
BIO tagging - BIO tagging represents labeled text spans through a tag attached to each token.
BIOES - BIOES is a token-labeling scheme that represents the boundaries and types of contiguous text spans.
Bitext word alignment - Definition: Bitext word alignment identifies corresponding words or tokens in two texts that express substantially the same content in different languages.
Bound pronoun - A bound pronoun is a pronoun interpreted as a variable whose value depends on a binding expression, often a quantified noun phrase.
Boundary tones - Boundary tones are tonal events associated with the edges of prosodic phrases in speech.
Bracketed notation - Bracketed notation represents a hierarchical structure as text by placing each unit and its contents inside matching brackets or parentheses.
Bridging inference - A bridging inference connects new information in a text to information already available by supplying an unstated relationship.
Brill tagger - Definition: A Brill tagger is a part-of-speech tagging system that begins with an initial set of word labels and applies an ordered sequence of learned...
Byte-pair encoding - Byte-pair encoding, or BPE, is a method that repeatedly merges frequent adjacent symbol pairs into larger symbols.
Cache language model - Definition: A cache language model adapts word or token predictions using a memory of previously encountered text.
Capture group - A capture group is a part of a regular expression that records the text matched by a selected subpattern so it can be retrieved or reused.
CAT - CAT stands here for computer-aided translation, also called computer-assisted translation: a workflow in which software supports a human translator's work.
Cataphora - Cataphora is a reference pattern in which an expression is interpreted through another expression that appears later in the text or speech.
Categorial grammar - Definition: Categorial grammar is a family of grammatical approaches in which words receive categories describing how they combine with other expressions.
Centering Theory - Centering Theory is a framework for explaining local discourse coherence through the prominence of entities and the referring expressions used for them.
Cepstral coefficients - Cepstral coefficients are numerical values obtained by transforming a logarithmic spectral representation of a signal.
Cepstral mean and variance normalization - Definition: Cepstral mean and variance normalization, usually abbreviated CMVN, standardizes speech-feature coefficients by subtracting an estimated mean...
Character disjunction - Character disjunction is a regular-expression operation that allows one character position to match any member of a specified set.
Chart parsing - Chart parsing is a family of parsing methods that store and reuse hypotheses about the structure of portions of an input.
Chomsky-adjunction - Chomsky-adjunction, in the context-free grammar sense used here, is a recursive way of extending a constituent while retaining its category.
Clarification - Clarification is a conversational act that seeks to resolve uncertainty about what another participant said or meant.
Class-based n-gram - A class-based n-gram is a language model that predicts words using groups of words called classes.
Classifier head - A classifier head is the part of a neural model that converts learned representations into scores for a classification task.
Clefts - Clefts are sentence constructions that present a message in a divided structure, commonly highlighting one constituent against a supporting clause.
Clitic - A clitic is a linguistic element that depends on a neighboring host for its pronunciation while contributing grammatical information.
Closed class - A closed class is a grammatical word category whose membership is relatively stable and does not readily expand through ordinary creation of new words.
Closure, stop - A stop closure is the interval during production of a stop consonant when the relevant articulators form a complete obstruction in the vocal tract.
Cloze task - A cloze task asks a person or model to supply missing material in a text using the available context.
Code point - A code point is a numerical position in a coded character set. In Unicode, code points run from U+0000 to U+10FFFF.
Code switching - Code switching is the use of more than one language or language variety within a conversation, message or utterance.
Codebook - A codebook is a defined collection of representations identified by codes or indices.
Codec - A codec is a method or implementation for encoding and decoding a signal, commonly to store or transmit it efficiently.
Cold languages - Cold languages is a metaphorical label used in some linguistic discussions for languages with relatively sparse explicit reference, where listeners often...
Commissive speech act - A commissive speech act is an utterance that commits its speaker to a future course of action.
Common ground - Common ground is the information that participants in a conversation treat as shared, including relevant knowledge, beliefs and assumptions.
Common noun - A common noun is a noun used to name a class or kind of person, place, object, substance or idea, rather than functioning as a proper name.