Distributional Models of Word Meaning

By Alessandro Lenci. 2018

320 citations recorded by the source corpus.

Distributional semantics is a usage-based model of meaning, based on the assumption that the statistical distribution of linguistic items in context plays a key role in characterizing their semantic behavior. Distributional models build semantic representations by extracting co-occurrences from corpora and have become a mainstream research paradigm in computational linguistics. In this review, I present the state of the art in distributional semantics, focusing on its assets and limits as a model of meaning and as a method for semantic analysis.

Subfields: Artificial Intelligence, Cultural Studies

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Denis Paperno
2. Timothee Mickus
3. Kees van Deemter
4. Alessandro Lenci
5. Olivier Bonami
6. Mathieu Constant
7. Marco Baroni
8. K. Erk

In Cultural Studies

1. Timothee Mickus
2. Denis Paperno
3. Alessandro Lenci

Citations in the corpus

• What do you mean, BERT? Assessing BERT as a Distributional Semantics Model (2019, background): “DSMs are nowadays systematically represented using vector spaces (Lenci, 2018).”
• Understanding Natural Language Understanding Systems. A Critical Analysis (2023, background): “The relationship between meaning and linguistic co-occurrences is the focus of distributional semantics (Lenci 2008, 2018; Lenci and Sahlgren 2023), an approach to meaning that develops theories and methods for representing and acquiring semantic properties of linguistic items from their…”
• Distributional Effects of Gender Contrasts Across Categories (2019, background): “In distributional semantics (Lenci, 2018), the meaning of a word is represented in the mathematical form of a vector computed on the basis of the word’s contexts of occurrence in a large text corpus.”