Computational

Domain — 31 words

This page gathers the 31 dictionary entries belonging to the domain “Computational”, as labelled by Wiktionary. Each word leads to its full entry: definitions, etymology, pronunciation, examples.

  1. bag of words noun The collection of words from an unprocessed text without regard to grammar; a collection of word unigrams.
  2. cache language model noun A type of statistical language model that assigns probabilities to word sequences based on a probability distribution.
  3. chunker noun A software tool for dividing text into chunks.
  4. co-occurrence network noun A text analysis method that visually represents relationships among entities based on their co-occurrence in electronic text.
  5. collocation extraction noun The automated process of identifying and extracting word combinations that frequently appear together in a given corpus.
  6. computational humor noun A field within computational linguistics and artificial intelligence that leverages computers for research on humor.
  7. computational semantics noun The study of automating the creation and interpretation of meaning representations in natural language expressions.
  8. concordance noun A listing, usually tokenized, where every word or phrase in a corpus can be found alongside its immediate context in each usage.
  9. coreset noun A small set of points that approximates the shape of a larger point set, in the sense that applying some geometric measure to the two sets…
  10. distributional semantics noun A field of research focused on quantifying and categorizing the semantic similarities between linguistic items.
  11. distributional–relational database noun A type of database management system that enhances the semantics of structured data by using distributional word-vector representations.
  12. epsilon-machine noun A deterministic automaton consisting of a system of causal states and the transitions between them, functioning as the smallest possible…
  13. foundation model noun An AI model trained on comprehensive data, enabling its application across various use cases such as chatbots and generative AI.
  14. grammar induction noun The process of constructing a model that captures the characteristics of observed objects by learning a formal grammar.
  15. inside–outside–beginning noun A tagging scheme commonly employed in tasks such as named-entity recognition within computational linguistics.
  16. interlingual machine translation noun A classic method where the source language is converted into an abstract, language-independent representation called interlingua.
  17. keyness noun The statistical significance of a keyword's frequency in a given corpus, relative to a reference corpus.
  18. lexical resource noun A linguistic asset comprising information about the words and their meanings within one or more languages.
  19. lexical simplification noun A subtask of text simplification that swaps words or phrases in a text to make it simpler and easier to understand, reducing its complexity.
  20. lexical substitution noun The task of replacing a word with another word while maintaining the meaning and context of the original sentence or phrase.
  21. logic form noun The representation of natural language sentences in first-order logic, where concept predicates are combined through shared arguments.
  22. morphological dictionary noun A resource that documents the relationship between surface forms and their corresponding lexical forms.
  23. n-gram noun A contiguous sequence of n items (usually characters or words) from a given sequence of text or speech, used in analysis.
  24. node noun The word of interest in a KWIC, surrounded by left and right cotexts.
  25. rejection sampling noun A technique used to generate observations from a distribution by repeatedly sampling an approximation function that bounds the distribution…
  26. sentiment analysis noun The use of computers to process natural language in an attempt to identify and extract information about the writer's affective state.
  27. shingle noun A word-based n-gram.
  28. statistical semantics noun The study of estimation of the meanings of words by looking at patterns of words in huge collections of texts, using statistical methods.
  29. string substitution noun A mapping of letters to sets of strings, which creates a closed operation for regular and context-free languages.
  30. treebank noun A database (corpus) of sentences which are annotated with syntactic information, often in the form of a tree.
  31. trigram noun An n-gram consisting of three items from a sequence.

All domains · Search for a word