Functional Distributional Semantics

Emerson, Guy; Copestake, Ann

doi:10.18653/v1/w16-1605

Cited by 13 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This tells us that some aspects of the model-theoretic data are much more important than others and that some can even be detrimental. This finding echoes results in Emerson and Copestake (2016), which indicated that selecting particular relations from parsed data can improve performance on SimLex.…”

Section: Discussionsupporting

confidence: 79%

Distributional Semantics in the Real World: Building Word Vector Representations from a Truth-Theoretic Model

Kuzmenko¹,

Herbelot²

2019

Proceedings of the 13th International Conference on Computational Semantics - Short Papers

View full text Add to dashboard Cite

Distributional semantics models (DSMs) are known to produce excellent representations of word meaning, which correlate with a range of behavioural data. As lexical representations, they have been said to be fundamentally different from truth-theoretic models of semantics, where meaning is defined as a correspondence relation to the world. There are two main aspects to this difference: a) DSMs are built over corpus data which may or may not reflect 'what is in the world'; b) they are built from word co-occurrences, that is, from lexical types rather than entities and sets. In this paper, we inspect the properties of a distributional model built over a set-theoretic approximation of 'the real world'. To achieve this, we take the annotation a large database of images marked with objects, attributes and relations, convert the data into a representation akin to first-order logic and build several distributional models using various combinations of features. We evaluate those models over both relatedness and similarity datasets, demonstrating their effectiveness in standard evaluations. This allows us to conclude that, despite prior claims, truth-theoretic models are good candidates for building graded lexical representations of meaning.

show abstract

Section: Discussionsupporting

confidence: 79%

Distributional Semantics in the Real World: Building Word Vector Representations from a Truth-Theoretic Model

Kuzmenko¹,

Herbelot²

2019

Proceedings of the 13th International Conference on Computational Semantics - Short Papers

View full text Add to dashboard Cite

show abstract

“…Modeling SVO-s is important for tasks such as compositional event similarity using all three variables, and thematic fit modeling based on SV and VO associations separately. Traditional solutions are typ-ically based on clustering of word co-occurrence counts from a large corpus (Baroni and Lenci, 2010;Greenberg et al, 2015a,b;Emerson and Copestake, 2016). More recent solutions combine neural networks with tensor-based methods.…”

Section: Multivariable (Svo) Structures In Nlpmentioning

confidence: 99%

Multidirectional Associative Optimization of Function-Specific Word Representations

Gerz

Vulić

Rei

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

We present a neural framework for learning associations between interrelated groups of words such as the ones found in Subject-Verb-Object (SVO) structures. Our model induces a joint function-specific word vector space, where vectors of e.g. plausible SVO compositions lie close together. The model retains information about word group membership even in the joint space, and can thereby effectively be applied to a number of tasks reasoning over the SVO structure. We show the robustness and versatility of the proposed framework by reporting state-of-the-art results on the tasks of estimating selectional preference and event similarity. The results indicate that the combinations of representations learned with our task-independent model outperform task-specific architectures from prior work, while reducing the number of parameters by up to 95%.

show abstract

“…• Functional Distributional Semantics was first proposed by [Emerson, 2016]. FDS separates the modeling of words and individuals, and it defines meaning in terms of truth.…”

Section: Introductionmentioning

confidence: 99%

Learning Functional Distributional Semantics with Visual Data

Liu

Emerson

2022

Preprint

View full text Add to dashboard Cite

Functional Distributional Semantics is a recently proposed framework for learning distributional semantics that provides linguistic interpretability. It models the meaning of a word as a binary classifier rather than a numerical vector. In this work, we propose a method to train a Functional Distributional Semantics model with grounded visual data. We train it on the Visual Genome dataset, which is closer to the kind of data encountered in human language acquisition than a large text corpus. On four external evaluation datasets, our model outperforms previous work on learning semantics from Visual Genome

show abstract

Functional Distributional Semantics

Cited by 13 publications

References 41 publications

Distributional Semantics in the Real World: Building Word Vector Representations from a Truth-Theoretic Model

Distributional Semantics in the Real World: Building Word Vector Representations from a Truth-Theoretic Model

Multidirectional Associative Optimization of Function-Specific Word Representations

Learning Functional Distributional Semantics with Visual Data

Contact Info

Product

Resources

About