Development set - A development set is a collection of examples used to guide choices while building a machine-learning system.
Dialogue act - A dialogue act is the communicative function performed by an utterance or part of an utterance in a conversation.
Dictionary-based machine translation - Definition: Dictionary-based machine translation translates source expressions by looking up corresponding target-language entries in a bilingual dictionary.
Digit recognition - Digit recognition is the task of identifying digits from an input signal.
Digital divide - The digital divide is unequal access to, ability to use, or benefit from digital technologies and information.
Digitization - Digitization is converting information from a physical or analog form into a digital representation that a computer can store and process.
Diphthong - A diphthong is a vowel whose quality changes noticeably during its production within a single syllable.
Direct voice input - Definition: Direct voice input, or DVI, is a human - machine interaction method in which spoken commands provide input to a computer or control interface...
Directive speech act - A directive speech act is an utterance intended to get another person or system to do something.
Discount - In count-based language modeling, a discount reduces the probability mass assigned to observed events so that some mass can be allocated elsewhere...
Discourse - Discourse is connected language interpreted as a structured whole, such as a conversation, report, story, or article.
Discourse connectives - Discourse connectives are words or phrases that signal relationships between parts of a text or conversation.
Discourse deixis - Discourse deixis is reference to some aspect of a stretch of discourse, often using expressions such as “this” or “that.
Discourse-new - Discourse-new describes a referent that is being introduced into the current discourse rather than already being established in it.
Discourse-old - Discourse-old describes a referent that has already been established in the current discourse and is accessed again by a later expression.
Discourse parsing - Discourse parsing is the computational analysis of relationships and structure across parts of a text.
Discourse relation - Definition: A discourse relation is a meaning-based connection between stretches of text, such as explanation, contrast, elaboration or temporal sequence.
Discovery procedure - In the linguistic context of this glossary, a discovery procedure is a systematic method intended to derive a description of a language's structure from...
Disfluency - A disfluency is an interruption, hesitation, repetition, or revision in the flow of speech.
Disjunction - Disjunction is the logical operation commonly expressed as “or.
Distributional - relational database - A distributional - relational database is a database approach that combines structured relations with distributional representations of meaning.
Distributional semantics - Distributional semantics is an approach to representing meaning through patterns of language use, especially the contexts in which words or other...
Document-rotation denoising - Document-rotation denoising is a language-model pretraining task in which a document is cyclically shifted to start at a randomly chosen token, and the...
Document structuring - Document structuring is the natural-language-generation task of organizing selected information into a coherent document.
Document-term matrix - A document-term matrix is a numerical table representing documents through selected text features.
Dot product - The dot product of two real-valued vectors is the sum of the products of their corresponding components.
Dynamic programming - Dynamic programming is a method for solving a problem by combining solutions to smaller subproblems and reusing their results.
Dynamic time warping - Dynamic time warping, or DTW, aligns two sequences while allowing differences in their local timing.
Edge-factored - Edge-factored describes a structured model whose score for a graph or tree decomposes into contributions from its individual edges.
EDU - EDU stands for elementary discourse unit: a minimal segment used as a building block in a discourse analysis, especially Rhetorical Structure Theory.
Effect size - Effect size is a numerical description of how large a difference or association is.
Elman Networks - Elman networks are simple recurrent neural networks that feed the previous hidden state into the computation of the next hidden state.
Emission probabilities - Emission probabilities describe how likely particular observations are given a hidden state in a probabilistic model such as a hidden Markov model, or HMM.
Encoder-decoder - An encoder-decoder is a model architecture in which an encoder represents an input and a decoder uses that representation to produce an output.
End-to-end training - End-to-end training uses a downstream task objective to adjust parameters across a connected model, including earlier representation-building components.
Endpointing - Endpointing is deciding when a spoken utterance or input segment is complete enough for a speech system to finalize recognition or move to its next action.
Energy in frame - Energy in a frame is a measure of signal strength over a short segment of audio.
Entity-based coherence - Entity-based coherence is the continuity a text achieves through its references to people, things, organizations, and other discourse entities.
Entity grid - An entity grid is a table that represents how people, objects, and other discourse entities appear across the sentences of a document.
Entity linking - Entity linking is the task of connecting a mention in text to the appropriate entity record in a knowledge base.
Evaluation of machine translation - Evaluation of machine translation is the systematic assessment of automatically translated text or translation systems.
Event extraction - Event extraction is the process of identifying events described in text and representing selected information about them in a structured form.
Example-based machine translation - Example-based machine translation, or EBMT, translates new input by retrieving relevant bilingual examples and adapting their target-language counterparts.
Explicit semantic analysis - Explicit semantic analysis, usually abbreviated ESA, represents text as a weighted vector of named concepts drawn from a knowledge collection.
Extraposition - Extraposition is a grammatical construction in which a clause or phrase appears later in a sentence than in a corresponding more basic arrangement.
F-measure - F-measure is a family of evaluation scores that combine precision and recall into one number. The best-known member, F1, is their harmonic mean.
Factoid questions - Factoid questions seek a specific factual answer that can usually be expressed briefly, such as a person’s name, a place, a date, or a quantity.