Scribd Logo
Upload

Welcome to Scribd!

  • 45 views

    Distributional Semantics in Linguistic and Cognitive Research Article in Italian Journal of Linguistics

    Uploaded by

    Rodrigo Sanz
    The document discusses distributional semantics, which is a methodological principle for semantic analysis based on the distribution and co-occurrence of words. Distributional semantics represents word meanings as vectors based on their contexts of use in language data. It takes a contextual and usage-based view of meaning, in contrast to model-theoretic approaches that anchor meaning to extra-linguistic entities. Distributional semantic models learn word representations by analyzing their behavior in linguistic contexts using techniques like concordances and association measures.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Distributional Semantics in Linguistic and Cognitive Research Article in Italian Journal of Linguistics

    Uploaded by

    Rodrigo Sanz
    45 views3 pages
    The document discusses distributional semantics, which is a methodological principle for semantic analysis based on the distribution and co-occurrence of words. Distributional semantics represents word meanings as vectors based on their contexts of use in language data. It takes a contextual and usage-based view of meaning, in contrast to model-theoretic approaches that anchor meaning to extra-linguistic entities. Distributional semantic models learn word representations by analyzing their behavior in linguistic contexts using techniques like concordances and association measures.

    Original Title

    Distributional semantics in linguistic and cognitive research Article in Italian Journal of Linguistics

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses distributional semantics, which is a methodological principle for semantic analysis based on the distribution and co-occurrence of words. Distributional semantics represents word meanings as vectors based on their contexts of use in language data. It takes a contextual and usage-based view of meaning, in contrast to model-theoretic approaches that anchor meaning to extra-linguistic entities. Distributional semantic models learn word representations by analyzing their behavior in linguistic contexts using techniques like concordances and association measures.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    45 views3 pages

    Distributional Semantics in Linguistic and Cognitive Research Article in Italian Journal of Linguistics

    Uploaded by

    Rodrigo Sanz
    The document discusses distributional semantics, which is a methodological principle for semantic analysis based on the distribution and co-occurrence of words. Distributional semantics represents word meanings as vectors based on their contexts of use in language data. It takes a contextual and usage-based view of meaning, in contrast to model-theoretic approaches that anchor meaning to extra-linguistic entities. Distributional semantic models learn word representations by analyzing their behavior in linguistic contexts using techniques like concordances and association measures.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 3

    Distributional semantics in linguistic and cognitive research

    Article in Italian Journal of Linguistics · January 2008

    Outside generative grammar, cognitive linguistics has stressed a conceptualist view of


    semantics, according to which the meaning of a lexical expression is a particular
    conceptualization of an entity or situation it is able to evoke. The definition of
    conceptualization given by Langacker is illuminating to understand the particular view of
    semantics favored in cognitive linguistics:

    “The term conceptualization is interpreted broadly as embracing any kind of mental


    experience. It subsumes (a) both established and novel conceptions; (b) not only abstract or
    intellectual “concepts” but also sensory, motor and emotive experience; and (c) full
    apprehension of the physical, social, cultural, and linguistic context (Langacker 1998:3)”

    Although the linguistic context appears as one of the ingredients of human


    conceptualization, the emphasis of cognitive semantics is on an intrinsically embodied
    conceptual representation of aspects of the world, grounded in action and perception
    systems. The distributional constraints to which linguistic constructions obey are intended to
    receive a functional explanation in terms of the principles governing our processes of
    conceptualizing the world. Therefore, it is embodied conceptualization to be the source of
    meaning and to explain linguistic distributions, rather than the other way round.

    Logico-philosophical and formal models of language have always emphasized a denotational


    approach to semantics, within the tradi tion of model-theoretic and referential semantics of
    Gottlob Frege, Alfred Tarski, Rudolf Carnap, Donald Davidson, Richard Montague, among
    many others. The basic tenet of this view is best described by David Lewis’s
    statement that “Semantics with no treatment of truth-conditions is not
    semantics” (Lewis 1972:169).

    Even if we admitted that distributional analysis tells us something interesting at all about
    language, this could not be said to be something about meaning

    cogitive approaches and model-theoretic ones agree on refusing distributional semantics


    because meaning can not be explained in terms of language-internal word distributions, but
    needs to be anchored onto extra-linguistic entities, being them either conceptual
    representations in the speakers’ mind or objects in the world.

    J.R. Firth “You shall know a word by the company it keeps” (Firth 1957:11)

    Semantica distribucional  methodological principle for semantic analysis.

    The distributional method is indeed common in lexicography, which keeps an unbreakable


    tie with corpus linguistics. Corpora and statistical methods to analyze the word behavior in
    contexts (e.g. concordances, association measures, etc.) are parts and parcels of the
    lexicographer’s toolbox.
    In psychology, the DH finds one of its strongest and explicit assertions (under the name of
    Contextual Hypothesis) in the work by George Miller and Walter Charles, who argue for a
    “usage-based” characterization of semantic representations:
    “What people know when they know a word is not how to recite its dictionary definition –
    they know how to use it (when to produce it and how to understand it) in everyday discourse
    [...]. Knowing how to use words is a basic component of knowing a language, and how that
    component is acquired is a central question for linguists and cognitive psychologists alike.
    The search for an answer can begin with the cogent assumption that people learn how to use
    words by observing how words are used. And because words are used together in phrases
    and sentences, this starting assumption directs attention immediately to the importance of
    context (Miller & Charles 1991:)”

    CONTEXTUAL REPRESENTATION

    Miller and Charles try to turn this general claim into a more operative “context-based”
    characterization of word meaning. In fact, they argue that repeated encounters of a word in
    the various linguistic contexts eventually determine the formation of a contextual
    representation, defined as follows: the cognitive representation of a word is some
    abstraction or generalization derived from the contexts that have been encountered. That
    is to say, a word’s contextual representation is not itself a linguistic context, but is an
    abstract cognitive structure that accumulates from encounters with the word in various
    (linguistic) contexts. The information that it contains characterizes a class of contexts
    (Ibidem:5; the emphasis is mine).

    Miller George A. & Walter G. Charles 1991. Contextual correlates of semantic similarity.
    Language and Cognitive Processes VI. 1-28.

     Distributional semantics offers both a model to represent meaning with vectors and computational
    methods to learn such representations from language data (but not only ...)

     cf. Multimodal Distributional Semantics (Feng & Lapata 2012, Bruni et al. 2014) Distributional representations
    are continuous and gradable

     Distributional semantics is based on a contextual and usage-based view of meaning

     The output of DSMs is a measure of semantic similarity/relatedness Distributional semantics is


    primarily a model of the lexicon

    “words are not mental objects that reside in a mental lexicon. They are operators on
    mental states. From this perspective, words do not have meaning; they are rather cues to
    meaning” (Elman 2014: 129)
    Erk K. 2012. Vector Space Models of Word Meaning and Phrase Meaning: A Survey.
    Linguistics and Language Compass 6:635–653
    Erk K. 2016. What do you know about an alligator when you know the company it keeps?
    Semantics & Pragmatics 9:1–63
    Erk K, McCarthy D, Gaylord N. 2013. Measuring Word Meaning in Context. Computational
    Linguistics 39:511–554

    In standard distributional semantics, each word is assigned a single vector, which is an


    abstraction over all its contexts of use, thus encompassing all the word senses that are

    3.1. Single representation, polysemy via composition

    The predominant, single representation approach is similar in spirit to structured ap- proaches to the lexicon like the
    Generative Lexicon (Pustejovsky 1995), Frame Semantics (Fillmore et al. 2006),

    These approaches aim at encoding all the relevant information in the lexical entry, and then define mechanisms to deploy the
    right meaning in context, usually by composition. As an example, Pustejovsky (1995, 122-123) formalizes two readings of
    bake, a change of state (John baked the potato) and a creation sense (John baked the cake), by letting the lexical entries of the
    verb and the noun interact: If bake combines with a mass-denoting noun, the change of state sense emerges; if it combines
    with an artifact, the creation sense emerges.

    You might also like