Dependency-Based Construction of Semantic Space Models

2007/06/01 by Sebastian Padó, Mirella Lapata · 701 citations
Computer Science · #Artificial intelligence #Class (philosophy) #Computer science #Dependency (UML) #Distributional semantics #Meaning (existential) #Natural Language Processing Techniques #Natural language processing #Priming (agriculture) #Process (computing) #Programming language #Semantic compression #Semantic computing #Semantic similarity #Semantic space #Semantic technology #Semantics (computer science) #Space (punctuation) #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.1162/coli.2007.33.2.161

published in Computational Linguistics 33(2), 161-199 (Association for Computational Linguistics)

openalex publication_date 2007/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

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 constructing semantic spaces that takes syntactic relations into account. We introduce a formalization for this class of models, which allows linguistic knowledge to guide the construction process. We evaluate our framework on a range of tasks relevant for cognitive science and natural language processing: semantic priming, synonymy detection, and word sense disambiguation. In all cases, our framework obtains results that are comparable or superior to the state of the art.

Citations

• A solution to Plato's problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge.
• Development and application of a metric on semantic nets
• A vector space model for automatic indexing
• Producing high-dimensional semantic spaces from lexical co-occurrence

Cited by

• High-dimensional distributed semantic spaces for utterances
• Distributional semantics [wikipedia]