Corpus ID: 1194205

Intensionality was only alleged: On adjective-noun composition in distributional semantics

@inproceedings{Boleda2013IntensionalityWO,
  title={Intensionality was only alleged: On adjective-noun composition in distributional semantics},
  author={Gemma Boleda and Marco Baroni and N. Pham and L. McNally},
  booktitle={IWCS},
  year={2013}
}
We acknowledge the support of Spanish MICINN grant FFI2010-09464-E (McNally, Boleda), the ICREA Foundation (McNally), Catalan AGAUR grant 2010BP-A00070, MICINN grant TIN2009-14715-C04-04, EU grant PASCAL2, FP7-ICT-216886, the DARPA DEFT program under AFRL grant FA8750-13-2-0026 (Boleda) and the ERC under the 2011 Starting Independent Research Grant 283554 to the COMPOSES project (Baroni, Pham). Any opinions, findings, and conclusions or recommendations expressed in this material are those of… Expand
Not logical : A distributional semantic account of negated adjectives
The meaning of a negated adjective does not always correspond to the one of its antonym (e.g., not small 6= large); indeed, linguistic theories and experimental data suggest that one of the functionsExpand
Inference with Distributional Semantic Models by Germán
CIMeC Doctoral School in Cognitive and Brain Sciences Doctor of Philosophy by Germán David Kruszewski Martel Distributional Semantic Models have emerged as a strong theoretical and practical approachExpand
Inference Patterns with Intensional Adjectives
TLDR
An initial annotation specification is created that is used to create a corpus of adjectiverelated inferences in English, focusing here on a subset of intensional adjectives typically referred to as “non-subsective” predicates. Expand
Kinds, descriptions of kinds, concepts, and distributions
Within referential approaches to meaning, Carlson’s (1977) notion of kind as an entity has played an in uential role not only in the analysis of generic sentences, but also in the analysis of commonExpand
Studying the Recursive Behaviour of Adjectival Modification with Compositional Distributional Semantics
TLDR
This study uses compositional distributional semantic methods to investigate restrictions in adjective ordering and finds that it is able to distinguish the relevant classes and the correct order based primarily on the degree of modification of the adjectives. Expand
Chaining and historical adjective extension
TLDR
This work examines how adjectives extend over time to describe nouns and form previously unattested adjectivenoun pairings to support a chaining mechanism that is sensitive to semantic neighbourhood density, best captured by an exemplar model of category extension. Expand
Identification of Adjective-Noun Neologisms using Pretrained Language Models
TLDR
The results show that the use of pretrained language models significantly improves over baseline linguistic features, however the combination with linguistic features still further improves the results, suggesting the strength of a hybrid approach. Expand
Adjective Noun Pretrained Language Model GloVe Vector GloVe Vector Freq Freq Softmax
  • 2019
Intensionality of Adjectives
TLDR
As is obvious to a native English speaker, the adjective (A) “fake” somehow modifies the noun (N) "cat” such that it no longer belongs to the set of N (cats) by virtue of being A (fake). Expand
Integrating Type Theory and Distributional Semantics: A Case Study on Adjective–Noun Compositions
TLDR
An integration of a formal semantic approach to lexical meaning and an approach based on distributional methods is explored and an algebraic interpretation of that formal semantic theory is developed and shown how to integrate the information provided by distributional models back into the formal semantic framework. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
First Order vs. Higher Order Modification in Distributional Semantics
TLDR
Observations concerning the attested vectors for the different types of adjectives, the nouns they modify, and the resulting noun phrases yield insights into modification that have been little evident in the formal semantics literature to date. Expand
A Regression Model of Adjective-Noun Compositionality in Distributional Semantics
In this paper we explore the computational modelling of compositionality in distributional models of semantics. In particular, we model the semantic composition of pairs of adjacent EnglishExpand
Some problems concerning the logic of grammatical modifiers
This paper consists principally of selections from a much longer work on the semantics of English. It discusses some problems concerning how to represent grammatical modifiers (e.g. ‘slowly’ in ‘xExpand
Events and Modification in Nominals
TLDR
It is proposed that interactions between nouns and adjectives yield evidence for an event argument inside the nominal as well, and this position seems to exist in both of the nominal projections countenanced by current linguistic theory: DP and NP. Expand
Frege in Space: A Program for Composition Distributional Semantics
The lexicon of any natural language encodes a huge number of distinct word meanings. Just to understand this article, you will need to know what thousands of words mean. The space of possibleExpand
Composition in Distributional Models of Semantics
TLDR
This article proposes a framework for representing the meaning of word combinations in vector space in terms of additive and multiplicative functions, and introduces a wide range of composition models that are evaluated empirically on a phrase similarity task. Expand
Entailment above the word level in distributional semantics
TLDR
Two ways to detect entailment using distributional semantic representations of phrases are introduced and nominal and quantifier phrase entailment appears to be cued by different distributional correlates, as predicted by the type-based view of entailment in formal semantics. Expand
Lexical Meaning in Context - A Web of Words
TLDR
The purpose of this monograph is to introduce the reader to the concept of type presuppositions and to discuss their application in the context of type-composition logic. Expand
Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space
TLDR
This work proposes an approach to adjective-noun composition (AN) for corpus-based distributional semantics that represents nouns as vectors and adjectives as data-induced (linear) functions over nominal vectors, and shows that the model significantly outperforms the rivals on the task of reconstructing AN vectors not seen in training. Expand
Vector Space Models of Lexical Meaning
TLDR
The meanings of words will be represented using vectors, as part of a high-dimensional " semantic space", namely the mathematical framework of vector spaces and linear algebra. Expand
...
1
2
3
...