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 USING CONCORDANCE AND CORPORA TECHNOLOGIES TO RESEARCH THE CONCEPT OF HEALTH/HEALTH

2020 ◽  
Vol 11 (87) ◽  
Author(s):  
Denys Shvaiber ◽  
◽  
Natalia Romanyshyn ◽  
Keyword(s):  
Los Angeles ◽  
Language Learning ◽  
Corpus Linguistics ◽  
Word Meaning ◽  
New York Times ◽  
Main Task ◽  
Lexical Unit ◽  
Lexical Meaning ◽  
Text Corpora ◽  
Media Texts

The article discusses the notion of concordance as a kind of dictionary of compatibility, which allows to analyze different contexts, to deduce shades of word meaning on their basis, to model semantic fields of correlated words in different languages. The aim of the article is to reveal the methodology of using the technologies of composing corpora of texts and concordances to build a nominative field of the concept HEALTH in English and Ukrainian media texts. The study was based on media texts on medicine, health and coronavirus in English and Ukrainian media texts (newspapers and magazines: USA Today, The Wall Street Journal, The New York Times, Los Angeles Times, The Washington Post, Vysokyi zamok, Ukrainska pravda; online edition: www.bbc. com/ukrainian/, www.bbc. com/news, time.com/, www.nytimes.com/, www.who.int; Gazeta.ua, Holos Ameryky, Hromadskyi prostir, Ukrainskyi tyzhden, Yevropeiska pravda, Hromadske.ua, Ukraina moloda and others). It is illustrated how concordance reflects all cases of use of words in this or that text, corpora of texts; the keywords of the researched concept are searched and the frequency of their use is determined. The use of concordance and corpus technologies (works by A. McCarthy and R. Carter, O'Keefe) is usually associated in linguistics with the study of the semantics of language units based on the calculation of word frequency, keywords, cluster analysis, etc., lexical and grammatical profiles. Work of users with the case is carried out by means of the specialized software – case managers who provide various opportunities on reception of the necessary information from the case. Concordance programs are used in a variety of areas: language learning and learning, language data search and analysis, translation and language engineering, corpus linguistics, lexicography, content analysis in accounting, history, marketing, music, politics, geography, journalism, and more. With concordance, you can create indexes and glossaries, calculate the frequency of use of a word, compare different uses of the word, analyze keywords, find phrases and idioms, create a concordance of one author, and so on. The main task of the concordance is to display all cases of use of the word registered in some texts. The possibility of realization of lexical meaning in the text is demonstrated, which helps to determine the role of lexical unit in the formation of textual conceptual structure.

scholarly journals Using distributional semantics to study syntactic productivity in diachrony: A case study

Linguistics ◽  
2016 ◽  
Vol 54 (1) ◽  
Author(s):  
Florent Perek
Keyword(s):  
Semantic Similarity ◽  
Empirical Studies ◽  
Data Driven ◽  
Distributional Semantics ◽  
Lexical Meaning ◽  
Text Corpora ◽  
Data Driven Approach

AbstractThis paper investigates syntactic productivity in diachrony with a data-driven approach. Previous research indicates that syntactic productivity (the property of grammatical constructions to attract new lexical fillers) is largely driven by semantics, which calls for an operationalization of lexical meaning in the context of empirical studies. It is suggested that distributional semantics can fulfill this role by providing a measure of semantic similarity between words that is derived from lexical co-occurrences in large text corpora. On the basis of a case study of the construction “V

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 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 Word meaning access: The one-to-many mapping from form to meaning

2019 ◽  
Author(s):  
Jennifer M Rodd
Keyword(s):  
A Priori ◽  
Word Meaning ◽  
Semantic Features ◽  
Contextual Cues ◽  
Word Meanings ◽  
Wide Range ◽  
Core Feature ◽  
Distributional Information ◽  
Current Context ◽  
The One

This chapter focuses on the process by which stored knowledge about a word’s form (orthographic or phonological) maps onto stored knowledge about its meaning. This mapping is made challenging by the ambiguity that is ubiquitous in natural language: most familiar words can refer to multiple different concepts. This one-to-many mapping from form to meaning within the lexicon is a core feature of word-meaning access. Fluent, accurate word-meaning access requires that comprehenders integrate multiple cues in order to determine which of a word’s possible semantic features are relevant in the current context. Specifically, word-meaning access is guided by (i) distributional information about the a priori relative likelihoods of different word meanings and (ii) a wide range of contextual cues that indicate which meanings are most likely in the current context.

Using Speakers' Referential Intentions to Model Early Cross-Situational Word Learning

2009 ◽  
Vol 20 (5) ◽  
pp. 578-585 ◽  
Author(s):  
Michael C. Frank ◽  
Noah D. Goodman ◽  
Joshua B. Tenenbaum
Keyword(s):  
Computational Model ◽  
Word Learning ◽  
Word Meaning ◽  
Mutual Exclusivity ◽  
Object Individuation ◽  
Word Meanings ◽  
Inference Problems ◽  
Corpus Data ◽  
Situational Learning

Word learning is a “chicken and egg” problem. If a child could understand speakers' utterances, it would be easy to learn the meanings of individual words, and once a child knows what many words mean, it is easy to infer speakers' intended meanings. To the beginning learner, however, both individual word meanings and speakers' intentions are unknown. We describe a computational model of word learning that solves these two inference problems in parallel, rather than relying exclusively on either the inferred meanings of utterances or cross-situational word-meaning associations. We tested our model using annotated corpus data and found that it inferred pairings between words and object concepts with higher precision than comparison models. Moreover, as the result of making probabilistic inferences about speakers' intentions, our model explains a variety of behavioral phenomena described in the word-learning literature. These phenomena include mutual exclusivity, one-trial learning, cross-situational learning, the role of words in object individuation, and the use of inferred intentions to disambiguate reference.

Kennis van Lexicale Relaties Bij Blinde Kinderen

1998 ◽  
Vol 60 ◽  
pp. 47-52
Author(s):  
Anita van Loon-Vervoorn ◽  
Loekie Eibers
Keyword(s):  
Mother Tongue ◽  
Word Meaning ◽  
Word Meanings ◽  
Blind Children

Blind children acquire their mother tongue in a relatively 'decontextualized' way, as compared to their sighted peers. Many word meanings which sighted children learn in a predominantly visual experiential context, have to be verbally explained and defined to blind children. In consequence, blind children may be deficient in the more experientially based aspects of word meaning, but may be aheadof their,sighted peers in their acquisition of the more verbally based meaning relations between words. Our findings indicate that blind children do not seem to be 'ahead' of sighted children in the knowledge about verbally based relations but rather in the accessibility of the relations which they have in their lexicon.

The Acquisition of Color Words

2017 ◽  
Author(s):  
Katie Wagner ◽  
David Barner
Keyword(s):  
Color Word ◽  
Inductive Learning ◽  
Word Meaning ◽  
Three Dimensional ◽  
Electromagnetic Spectrum ◽  
Word Meanings ◽  
Word Acquisition ◽  
Color Categories ◽  
Word Boundaries ◽  
Different Color

Human experience of color results from a complex interplay of perceptual and linguistic systems. At the lowest level of perception, the human visual system transforms the visible light portion of the electromagnetic spectrum into a rich, continuous three-dimensional experience of color. Despite our ability to perceptually discriminate millions of different color shades, most languages categorize color into a number of discrete color categories. While the meanings of color words are constrained by perception, perception does not fully define them. Once color words are acquired, they may in turn influence our memory and processing speed for color, although it is unlikely that language influences the lowest levels of color perception. One approach to examining the relationship between perception and language in forming our experience of color is to study children as they acquire color language. Children produce color words in speech for many months before acquiring adult meanings for color words. Research in this area has focused on whether children’s difficulties stem from (a) an inability to identify color properties as a likely candidate for word meanings, or alternatively (b) inductive learning of language-specific color word boundaries. Lending plausibility to the first account, there is evidence that children more readily attend to object traits like shape, rather than color, as likely candidates for word meanings. However, recent evidence has found that children have meanings for some color words before they begin to produce them in speech, indicating that in fact, they may be able to successfully identify color as a candidate for word meaning early in the color word learning process. There is also evidence that prelinguistic infants, like adults, perceive color categorically. While these perceptual categories likely constrain the meanings that children consider, they cannot fully define color word meanings because languages vary in both the number and location of color word boundaries. Recent evidence suggests that the delay in color word acquisition primarily stems from an inductive process of refining these boundaries.

Sign in / Sign up

Export Citation Format

Share Document