Subwords - Subwords are text units smaller than a whole word that can be used as tokens in language-processing systems.
Syllabification - Syllabification is the process of dividing a spoken form, or a representation of that form, into syllables.
Syllable - A syllable is a unit of spoken language organized around a central nucleus, usually a vowel, with optional surrounding consonants.
Symbolic linguistic representation - A symbolic linguistic representation describes language using explicit labels, categories and relationships with defined interpretations.
Synchronous context-free grammar - A synchronous context-free grammar is a formal grammar that generates linked pairs of structures or strings.
Synonyms - Synonyms are words or expressions with the same or closely similar meanings in a particular sense or context.
Template filling - Template filling is an information-extraction task that converts descriptions of recurring situations or events into structured records with predefined fields.
Template recognition - In information extraction, template recognition is the task of deciding whether a piece of text describes an instance of a situation or event type...
Temporal adverb - A temporal adverb is an adverb that contributes information about time, such as “yesterday,” “soon,” or “recently.
Temporal anchor - A temporal anchor is a reference time used to interpret a time expression or locate an event.
Temporal annotation - Temporal annotation is the addition of structured labels describing time-related information in language.
Temporal expressions - Temporal expressions are words, numbers or phrases that refer to time.
Term weight - A term weight is a numerical value assigned to a term in a text representation or retrieval model to control its contribution to a score.
Terminal symbol - A terminal symbol is a symbol that appears in the completed strings generated by a formal grammar.
Text corpus - A text corpus is an organized collection of texts assembled for a defined purpose, such as studying language, training a model or evaluating a...
Text graph - A text graph is a graph representation built from language material.
Text mining - Text mining is the computational analysis of text collections to identify useful patterns, relationships or information.
Text nailing - Text Nailing is a named information-extraction method associated with Uri Kartoun and colleagues.
Text simplification - Text simplification is the rewriting of text to make it easier for an intended audience to read and understand while preserving the required meaning.
Text-to-speech - Text-to-speech, often abbreviated TTS, is technology that converts written text into spoken audio.
Text-to-video model - A text-to-video model is a generative model that produces video conditioned on a written description.
Textual case-based reasoning - Textual case-based reasoning uses descriptions of previous situations, problems or experiences written in natural language to help address a new situation.
Textual entailment - Textual entailment is the relationship in which the meaning of one text supports an inference expressed by another text.
Thematic grid - A thematic grid is a representation of the semantic participant roles associated with a verb or a particular verb sense.
Thematic role - A thematic role describes the semantic relationship between a participant and the event or situation expressed by a predicate.
Theme - In linguistic semantics, a theme is a participant role commonly assigned to an entity whose location or movement is described, or, in broader role...
Time-compressed speech - Time-compressed speech is recorded speech processed to play in less time.
Time-inhomogeneous hidden Bernoulli model - A time-inhomogeneous hidden Bernoulli model, or TI-HBM, is a probabilistic acoustic model proposed for speech recognition.
Toxicity detection - Toxicity detection is the use of computational methods to identify language that meets a defined criterion for harmful, abusive, disrespectful, or...
Training oracle - A training oracle is a procedure that uses a known reference answer to provide guidance for a model’s training decisions.
Transduction grammars - Transduction grammars are formal systems that describe correspondences between structured expressions, commonly between sentences in two languages.
Transfer-based machine translation - Transfer-based machine translation is an approach that analyses text in a source language, maps the resulting representation into a target-language...
Transition-based - Transition-based describes an approach that constructs an output through a sequence of state-changing actions.
Translation memory - A translation memory is a database of previously translated text segments paired with their corresponding translations.
Translation unit - A translation unit is a portion of text treated as a meaningful whole when translating.
Treebank - A treebank is a collection of sentences annotated with syntactic structures.
Triphone - A triphone is a context-dependent representation of a speech sound that includes its immediate left and right phonetic neighbors.
Two-stream self-attention - Two-stream self-attention is XLNet's mechanism for maintaining separate content and query representations at token positions.
Unicode - Unicode is a standard for representing and processing text across writing systems.
Unit production - A unit production is a context-free grammar rule whose right-hand side consists of exactly one nonterminal symbol, such as A→B.
Unlikelihood training - Unlikelihood training adds an objective that lowers the probability of selected undesirable outputs.
Unvoiced sound - An unvoiced sound, also called a voiceless sound, is produced without the regular vocal-fold vibration that supplies voicing.
UTF-8 - UTF-8 is a Unicode encoding that represents each Unicode scalar value using one to four bytes.
Utterance - An utterance is a particular instance or segment of language produced in communication, commonly a stretch of speech by a speaker in context.
Variable-length encoding - Definition: Variable-length encoding represents different items using code sequences of different lengths.