Semantic relations

thumb|Synonym list in cuneiform on a clay tablet, [[Neo-Assyrian period]]

In lexical semantics, opposites are words lying in an inherently incompatible binary relationship. For example, something that is even entails that it is not odd. It is referred to as a 'binary' relationship because there are two members in a set of opposites. The relationship between opposites is known as opposition. A member of a pair of opposites can generally be determined by the question: "What is the opposite of X"

Polysemy ( or ; ) is the capacity for a sign (e.g. a symbol, morpheme, word, or phrase) to have multiple related meanings. For example, a word can have several word senses. Polysemy is the opposite of monosemy, which denotes a word with a single meaning.

thumb|400px|Venn diagram showing the relationships between homophones (blue circle) and related linguistic concepts

Process of reinterpretive word formation

Paronyms are near-homophones ("soundalike"), near-homographs ("lookalike") and/or near-cognates ("meanalike") — words that are similar but not identical in pronunciation, spelling, or lexical meaning — which may cause confusion in their understanding (reception) and usage (production). Paronymy is the relationship between a pair of words or phrases which are similar or partially identical in spelling, pronunciation and/or meaning.

In corpus linguistics, a collocation is a series of words or terms that co-occur more often than would be expected by chance. In phraseology, a collocation is a type of compositional phraseme, meaning that it can be understood from the words that make it up. This contrasts with an idiom, where the meaning of the whole cannot be inferred from its parts, and may be completely unrelated.

A retronym is a newer name for something that differentiates it from something else that is newer, similar, or seen in everyday life, thus avoiding confusion between the two.

set of words grouped by meaning referring to a specific subject

technique in natural language processing that represents words as vectors in a continuous vector space

directed graph structure with labeled edges serving to encode and represent knowledge, whether knowledge of definitions or assertions

mode of graded categorization in cognitive science

form of language change regarding the evolution of word usage

set of semantic relations involving the type-of property

Word2vec is a technique in natural language processing for obtaining vector representations of words. These vectors capture information about the meaning of the word based on the surrounding words. The word2vec algorithm estimates these representations by modeling text in a large corpus. Once trained, such a model can detect synonymous words or suggest additional words for a partial sentence. Word2vec was developed by Tomáš Mikolov, Kai Chen, Greg Corrado, Ilya Sutskever and Jeff Dean at Google, and published in 2013.

two dissimilar translation approaches

knowledge organization system

Mereology (; from Greek μέρος 'part' (root: μερε-, mere-) and the suffix -logy, 'study, discussion, science') is the philosophical study of part-whole relationships, also called parthood relationships. As a branch of metaphysics, mereology examines the connections between parts and their wholes, exploring how components interact within a system. This theory has roots in ancient philosophy, with significant contributions from Plato, Aristotle, and later, medieval and Renaissance thinkers like Thomas Aquinas and John Duns Scotus. Mereology was formally axiomatized in the 20th century by Polish l

group of things connected by a series of overlapping similarities, where no one feature is common to all of the things

technique in natural language processing

word game

popularly held but false belief about the origin or derivation of a specific word

a rigorous method of deriving an ontology from a collection of objects and their properties

research area in semantic similarities between linguistic items

The suffix -onym (from ) is a bound morpheme, that is attached to the end of a root word, thus forming a new compound word that designates a particular class of names. In linguistic terminology, compound words that are formed with suffix -onym are most commonly used as designations for various onomastic classes. Most onomastic terms that are formed with suffix -onym are classical compounds, whose word roots are taken from classical languages (Greek and Latin).

Metric in computational linguistics

an area of supervised machine learning in artificial intelligence. It is closely related to regression and classification, but the goal is to learn from examples a similarity function that measures how similar or related two objects are

semantic relation of a part to the whole specific to linguistics

aspect of a linguistic unit

process of relating syntactic structures, from the levels of phrases, clauses, sentences and paragraphs to the level of the writing as a whole, to their language-independent meanings

A meronomy is a hierarchical taxonomy that deals with part–whole relationships. For example, a car has parts that include engine, body and wheels; and the body has parts that include doors and windows.

In linguistics, troponymy is the presence of a 'manner' relation between two lexemes.