Abstract
We address the task of computing vector space representations for the meaning of word occurrences, which can vary widely according to context. This task is a crucial step towards a robust, vector-based compositional account of sentence meaning. We argue that existing models for this task do not take syntactic structure sufficiently into account.
Keywords
Computer scienceMeaning (existential)SentenceWord (group theory)Task (project management)Context (archaeology)Natural language processingSpace (punctuation)Artificial intelligenceVector spaceLinguisticsMathematicsPsychologyHistoryEngineering
Affiliated Institutions
Related Publications
Dependency-Based Construction of Semantic Space Models
Traditionally, vector-based semantic space models use word co-occurrence counts from large corpora to represent lexical meaning. In this article we present a novel framework for...
Compositional Matrix-Space Models of Language
We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structura...
Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics
Speakers of a language can construct an unlimited number of new words through morphological derivation. This is a major cause of data sparseness for corpus-based approaches to l...
Experimental Support for a Categorical Compositional Distributional Model of Meaning
Modelling compositional meaning for sentences using empirical distributional methods has been a challenge for computational linguists. We implement the abstract categorical mode...
Composition in Distributional Models of Semantics
Abstract Vector‐based models of word meaning have become increasingly popular in cognitive science. The appeal of these models lies in their ability to represent meaning simply ...
Publication Info
- Year
- 2008
- Type
- article
- Pages
- 897-897
- Citations
- 362
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
362
OpenAlex
Cite This
Katrin Erk,
Sebastian Padó
(2008).
A structured vector space model for word meaning in context.
, 897-897.
https://doi.org/10.3115/1613715.1613831
Identifiers
- DOI
- 10.3115/1613715.1613831