A practical and linguistically-motivated approach to compositional distributional semantics

@inproceedings{Paperno2014APA,
  title={A practical and linguistically-motivated approach to compositional distributional semantics},
  author={Denis Paperno and N. Pham and Marco Baroni},
  booktitle={ACL},
  year={2014}
}
Distributional semantic methods to approximate word meaning with context vectors have been very successful empirically, and the last years have seen a surge of interest in their compositional extension to phrases and sentences. We present here a new model that, like those of Coecke et al. (2010) and Baroni and Zamparelli (2010), closely mimics the standard Montagovian semantic treatment of composition in distributional terms. However, our approach avoids a number of issues that have prevented… Expand
Compositional distributional semantics with compact closed categories and Frobenius algebras
TLDR
In the proposed extension, the concept of a distributional vector is replaced with that of a density matrix, which compactly represents a probability distribution over the potential different meanings of the specific word. Expand
Leveraging Preposition Ambiguity to Assess Compositional Distributional Models of Semantics
TLDR
A new method is presented for assessing the degree to which CDSM capture semantic interactions that dissociates the influences of lexical and compositional information and shows that neural language input vectors are consistently superior to co-occurrence based vectors and vector addition matches and is in many cases superior to purpose-built paramaterized models. Expand
Sentential Representations in Distributional Semantics
TLDR
This thesis puts more focus on unsupervised methods which make use of the context of phrases and sentences to optimize the parameters of a model, and makes three principal contributions to the field of compositional distributional semantics. Expand
The Categorial Framework for Compositional Distributional Semantics
This technical report is concerned with the integration of formal semantics [52, 18] and distributional semantics [62, 70, 11]. Several current attempts at this integration [42, 23, 29] effectivelyExpand
Deriving Boolean structures from distributional vectors
TLDR
This Boolean Distributional Semantic Model (BDSM) achieves results comparable to a state-of-the-art SVM, degrades more gracefully when less training data are available and displays interesting qualitative properties. Expand
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
Typology of Adjectives Benchmark for Compositional Distributional Models
TLDR
The notion of typological closeness is introduced, which is a novel rigorous formalization of semantic similarity based on comparison of multilingual data that performs way above non-compositional alternatives on the task of prediction of lexical typology. Expand
A structured distributional model of sentence meaning and processing
TLDR
A structured distributional model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations is proposed. Expand
RELPRON: A Relative Clause Evaluation Data Set for Compositional Distributional Semantics
TLDR
The results show that vector addition is difficult to beat—in line with the existing literature—but that an implementation of the Categorial framework based on the Practical Lexical Function model is able to match the performance of vector addition. Expand
A dependency-based approach to word contextualization using compositional distributional semantics
We propose a strategy to build the distributional meaning of sentences, which is mainly based on two types of semantic objects: context vectors associated with content words and compositionalExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
Experimental Support for a Categorical Compositional Distributional Model of Meaning
TLDR
The abstract categorical model of Coecke et al. (2010) is implemented using data from the BNC and evaluated, with general improvement in results with increase in syntactic complexity showcasing the compositional power of the model. Expand
General estimation and evaluation of compositional distributional semantic models
TLDR
An evaluation of alternative cDSMs under truly comparable conditions is presented, and the linguistically motivated functional model of Baroni and Zamparelli and Coecke et al. (2010) emerges as the winner in all the authors' tests. Expand
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
Category-theoretic quantitative compositional distributional models of natural language semantics
TLDR
This thesis shows how the categorical framework developed by Coecke, Sadrzadeh, and Clark, which combines syntactic analysis formalisms with distributional semantic representations of meaning to produce syntactically motivated composition operations can be theoretically extended and practically implemented to produce concrete compositional distributional models of natural language semantics. 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
Experimenting with transitive verbs in a DisCoCat
TLDR
Transitive verbs, represented as matrices in a DisCoCat, are examined by examining three ways of constructing such matrices, and each method is evaluated in a disambiguation task developed by Grefenstette and Sadrzadeh (2011). 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
A relatedness benchmark to test the role of determiners in compositional distributional semantics
TLDR
This work explores whether compositional distributional semantic models can also handle a construction in which grammatical terms play a crucial role, namely determiner phrases (DPs). Expand
Estimating Linear Models for Compositional Distributional Semantics
TLDR
This paper proposes a novel approach to estimate parameters for a class of compositional distributional models: the additive models, and demonstrates that this approach outperforms existing methods for determining a good model for compositional distributionsal semantics. Expand
Separating Disambiguation from Composition in Distributional Semantics
TLDR
Evidence is provided that the addition of a vector disambiguation step prior to the actual composition would be beneficial to the whole process, producing better composite representations. Expand
...
1
2
3
...