Intensionality was only alleged: On adjective-noun composition in distributional semantics
نویسندگان
چکیده
Formal semantics has traditionally distinguished between extensional and intensional aspects of meaning, roughly equivalent to reference and what people intuitively call "meaning", respectively. It has primarily focused on extension, since this allows for predictions to be made and tested by building models of meaning that are directly grounded on reference, using set theoretic tools. Distributional semantics, in contrast, has been used to model phenomena that are hard to pinpoint using reference only, such as similarity in word meaning. Since the two approaches are largely complementary, it makes sense to use the latter to reexamine puzzles posed by the former.
منابع مشابه
Integrating Type Theory and Distributional Semantics: A Case Study on Adjective-Noun Compositions
In this article, we explore an integration of a formal semantic approach to lexical meaning and an approach based on distributional methods. First, we outline a formal semantic theory that aims to combine the virtues of both formal and distributional frameworks. We then proceed to develop an algebraic interpretation of that formal semantic theory and show how at least two kinds of distributiona...
متن کاملNouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space
We propose an approach to adjective-noun composition (AN) for corpus-based distributional semantics that, building on insights from theoretical linguistics, represents nouns as vectors and adjectives as data-induced (linear) functions (encoded as matrices) over nominal vectors. Our model significantly outperforms the rivals on the task of reconstructing AN vectors not seen in training. A small ...
متن کاملDistributional semantic phrases vs. semantic distributional nonsense: Adjective modification in compositional distributional semantics
In this talk, I discuss the ability of compositional distributional semantics to model adjective modification. I present three studies that explore the degree to which semantic intuitions are grounded in the distributional representations of adjective-noun phrases, as well as provide insight into various linguistic phenomena by extracting unsupervised cues from these distributional representati...
متن کاملComputing Semantic Compositionality in Distributional Semantics
This article introduces and evaluates an approach to semantic compositionality in computational linguistics based on the combination of Distributional Semantics and supervised Machine Learning. In brief, distributional semantic spaces containing representations for complex constructions such as Adjective-Noun and Verb-Noun pairs, as well as for their constituent parts, are built. These represen...
متن کاملDistributional Semantic Models of Attribute Meaning in Adjectives and Nouns
Attributes such as size, weight or color are at the core of conceptualization, i.e., the formal representation of entities or events in the real world. In natural language, formal attributes find their counterpart in attribute nouns which can be used in order to generalize over individual properties (e.g., big or small in case of size, blue or red in case of color). In order to ascribe such pro...
متن کامل