Distributional Semantics and Linguistic Theory
Распределённая семантика и лингвистическая теория
2019-10-21
SCID: 54.1/durvgkur
Discuss with AI
distributional semanticsgrammar–semantics interfacepolysemy and compositionsemantic changeword representations
Figures from the paper
Abstract (AI)
Distributional semantics provides multidimensional, graded, empirically induced word representations that successfully capture many aspects of meaning in natural languages, as shown by a large body of research in computational linguistics; yet, its impact in theoretical linguistics has so far been limited. This review provides a critical discussion of the literature on distributional semantics, with an emphasis on methods and results that are relevant for theoretical linguistics, in three areas: semantic change, polysemy and composition, and the grammar–semantics interface (specifically, the interface of semantics with syntax and with derivational morphology). The goal of this review is to foster greater cross-fertilization of theoretical and computational approaches to language as a means to advance our collective knowledge of how it works.
Key Findings
1
A large body of computational linguistics research demonstrates the empirical success of distributional semantic methods.
2
Despite empirical success, distributional semantics has had limited impact on theoretical linguistics to date.
3
Distributional semantics yields multidimensional, graded, empirically induced word representations that capture many aspects of natural language meaning.
4
Fostering cross-fertilization between theoretical and computational approaches is advocated as a means to advance understanding of language.
5
The review critically discusses distributional semantics research relevant to theoretical linguistics in three areas: semantic change, polysemy and composition, and the grammar–semantics interface (syntax and derivational morphology).
Research Object
Distributional semantics models / empirically induced multidimensional word representations
Research Subject
Their relevance and implications for theoretical linguistics, specifically effects on semantic change, polysemy and composition, and the grammar–semantics interface (syntax and derivational morphology)
Publication Details
Publication Date
2019-10-21
Journal
Publisher
ISSN
Cited by
328
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Distributed Representations of Words and Phrases and their Compositionality2013
Enriching Word Vectors with Subword Information2017
From Frequency to Meaning: Vector Space Models of Semantics2010
Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors2014
Composition in Distributional Semantics2013