scholarly journals Incremental Composition in Distributional Semantics

2021 ◽  
Author(s):  
Matthew Purver ◽  
Mehrnoosh Sadrzadeh ◽  
Ruth Kempson ◽  
Gijs Wijnholds ◽  
Julian Hough
Keyword(s):  
Vector Space ◽  
Set Theory ◽  
Predicate Logic ◽  
Word Meaning ◽  
Real Data ◽  
Distributional Semantics ◽  
Language Constructs ◽  
Dynamic Syntax ◽  
Lexical Content ◽  
Compositional Distributional Semantics

AbstractDespite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.

scholarly journals A generalised quantifier theory of natural language in categorical compositional distributional semantics with bialgebras

2019 ◽  
Vol 29 (06) ◽  
pp. 783-809
Author(s):  
Jules Hedges ◽  
Mehrnoosh Sadrzadeh
Keyword(s):  
Natural Language ◽  
Vector Space ◽  
Generative Grammar ◽  
Distributional Semantics ◽  
Compositional Semantics ◽  
Finite Dimensional ◽  
Linear Maps ◽  
First Time ◽  
Quantifier Theory ◽  
Compositional Distributional Semantics

AbstractCategorical compositional distributional semantics is a model of natural language; it combines the statistical vector space models of words with the compositional models of grammar. We formalise in this model the generalised quantifier theory of natural language, due to Barwise and Cooper. The underlying setting is a compact closed category with bialgebras. We start from a generative grammar formalisation and develop an abstract categorical compositional semantics for it, and then instantiate the abstract setting to sets and relations and to finite-dimensional vector spaces and linear maps. We prove the equivalence of the relational instantiation to the truth theoretic semantics of generalised quantifiers. The vector space instantiation formalises the statistical usages of words and enables us to, for the first time, reason about quantified phrases and sentences compositionally in distributional semantics.

scholarly journals Frege in Space: A Program for Compositional Distributional Semantics

2014 ◽  
Vol 9 ◽  
Author(s):  
Marco Baroni ◽  
Raffaella Bernardi ◽  
Roberto Zamparelli
Keyword(s):  
Formal Semantics ◽  
Word Meaning ◽  
Distributional Semantics ◽  
Huge Number ◽  
Word Meanings ◽  
New Approach ◽  
Lexical Meaning ◽  
Text Corpora ◽  
Distinct Word ◽  
Compositional 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 possible sentential meanings is infinite: In this article alone, you will encounter many sentences that express ideas you have never heard before, we hope. Statistical semantics has addressed the issue of the vastness of word meaning by proposing methods to harvest meaning automatically from large collections of text (corpora). Formal semantics in the Fregean tradition has developed methods to account for the infinity of sentential meaning based on the crucial insight of compositionality, the idea that meaning of sentences is built incrementally by combining the meanings of their constituents. This article sketches a new approach to semantics that brings together ideas from statistical and formal semantics to account, in parallel, for the richness of lexical meaning and the combinatorial power of sentential semantics. We adopt, in particular, the idea that word meaning can be approximated by the patterns of co-occurrence of words in corpora from statistical semantics, and the idea that compositionality can be captured in terms of a syntax-driven calculus of function application from formal semantics.

scholarly journals Compositional Distributional Semantics with Syntactic Dependencies and Selectional Preferences

2021 ◽  
Vol 11 (12) ◽  
pp. 5743
Author(s):  
Pablo Gamallo
Keyword(s):  
English Language ◽  
State Of The Art ◽  
Current Work ◽  
Distributional Semantics ◽  
Compositional Model ◽  
Compositional Approach ◽  
Sentence Similarity ◽  
Selectional Preferences ◽  
Syntactic Dependencies ◽  
Compositional Distributional Semantics

This article describes a compositional model based on syntactic dependencies which has been designed to build contextualized word vectors, by following linguistic principles related to the concept of selectional preferences. The compositional strategy proposed in the current work has been evaluated on a syntactically controlled and multilingual dataset, and compared with Transformer BERT-like models, such as Sentence BERT, the state-of-the-art in sentence similarity. For this purpose, we created two new test datasets for Portuguese and Spanish on the basis of that defined for the English language, containing expressions with noun-verb-noun transitive constructions. The results we have obtained show that the linguistic-based compositional approach turns out to be competitive with Transformer models.

scholarly journals When the Whole Is Not Greater Than the Combination of Its Parts: A “Decompositional” Look at Compositional Distributional Semantics

2015 ◽  
Vol 41 (1) ◽  
pp. 165-173 ◽  
Author(s):  
Fabio Massimo Zanzotto ◽  
Lorenzo Ferrone ◽  
Marco Baroni
Keyword(s):  
Distributional Semantics ◽  
Important Class ◽  
Strong Link ◽  
Composition Methods ◽  
Convolution Kernels ◽  
Composition Operations ◽  
Compositional Distributional Semantics

Distributional semantics has been extended to phrases and sentences by means of composition operations. We look at how these operations affect similarity measurements, showing that similarity equations of an important class of composition methods can be decomposed into operations performed on the subparts of the input phrases. This establishes a strong link between these models and convolution kernels.

scholarly journals Learning Lexical Subspaces in a Distributional Vector Space

2020 ◽  
Vol 8 ◽  
pp. 311-329
Author(s):  
Kushal Arora ◽  
Aishik Chakraborty ◽  
Jackie C. K. Cheung
Keyword(s):  
Vector Space ◽  
Semantic Relations ◽  
Distributional Semantics ◽  
Word Embeddings ◽  
Word Similarity ◽  
Lexical Semantic ◽  
Novel Approach ◽  
Classification Tasks

In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relation should hold. Our framework can handle symmetric attract and repel relations (e.g., synonymy and antonymy, respectively), as well as asymmetric relations (e.g., hypernymy and meronomy). In a suite of intrinsic benchmarks, we show that our model outperforms previous approaches on relatedness tasks and on hypernymy classification and detection, while being competitive on word similarity tasks. It also outperforms previous systems on extrinsic classification tasks that benefit from exploiting lexical relational cues. We perform a series of analyses to understand the behaviors of our model. 1 Code available at https://github.com/aishikchakraborty/LexSub .

scholarly journals Children’s Early Understanding of Mass–Count Syntax: Individuation, Lexical Content, and the Number Asymmetry Hypothesis

2016 ◽  
Author(s):  
David Barner ◽  
Jesses Snedeker
Keyword(s):  
Word Meaning ◽  
Age Groups ◽  
Mass Nouns ◽  
Count Nouns ◽  
Lexical Content

How does mass–count syntax affect word meaning? Many theorists haveproposed that count nouns denote individuals, whereas mass nouns do not(Bloom, 1999; Gordon, 1985; Link, 1983), a proposal that is supported byprototypical examples of each (table, water). However, studies of quantityjudgments in 4-year-olds and adults demonstrate that some mass nouns(furniture) do denote individuals (Barner & Snedeker, 2005). This isproblematic for bootstrapping theories that posit one-to-onesyntax-semantics mappings (individual ↔ count; nonindividual ↔ mass; Bloom,1999), unless mass nouns that denote individuals are late-learnedexceptions to mappings. This article investigates this possibility in3-year-olds and adults using 2 methods: word extension and quantityjudgment. Both methods indicate that novel mass nouns can denoteindividuals in both age groups, and thus fail to support simplifiedsyntax-semantics mappings. Also, differences between word extension andquantity judgment raise the possibility that the tasks measure differentunderlying knowledge.

A Semantic Map for Indoor Robot Navigation Based on Predicate Logic

2020 ◽  
Vol 11 (1) ◽  
pp. 1-21
Author(s):  
Hengsheng Wang ◽  
Jin Ren
Keyword(s):  
Natural Language ◽  
Indoor Environment ◽  
Robot Navigation ◽  
Predicate Logic ◽  
Constraint Satisfaction Problem ◽  
Real Data ◽  
Main Concern ◽  
Building Structure ◽  
Topological Map ◽  
Semantic Map

Interacting with mobile robots through natural language is the main concern of this article, which focuses on the semantic meaning of concepts used in natural language instructions to navigate robots indoors. Assuming the building structure is the prior knowledge of the robot and the robot has the ability of navigating itself locally to avoid collision with the environment, the building structure is represented with predicate logic on SWI-Prolog as the database of the indoor environment, which is called semantic map in this paper, in which the basic predicate clauses are based on two kinds of entities, namely ‘area' and ‘node.' The area names (in natural language convention) of indoor environment are organized with an ontology and are defined in the semantic map which includes the geometric information of areas and connection relationships between areas. With the semantic map database, functions for robot navigation, like a topological map, path planning, and self-localization, are realized through reasoning by properly designed predicates based on constraint satisfaction problem (CSP). An example building is given to show the idea proposed in this article, the real data of which was used to establish the semantic map, and the predicates for navigation functions worked well on SWI-Prolog.

Sign in / Sign up

Export Citation Format

Share Document