Antonymy and conceptual vectors

Schwab, Didier; Lafourcade, Mathieu; Prince, Violaine

doi:10.3115/1072228.1072289

Cited by 11 publications

(17 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown previously [7,[16][17][18][19]] that a conceptual vector can be improved by the effects of lexical functions, and also that the lexical function data themselves are significantly enhanced by the use of lexical information and of the corresponding vectors. Hence, the two processes of learning of lexical functions and the construction of new vectors are mutually benefiting each other, each feeding their outputs into the inputs of the other.…”

Section: Towards a Society Of Agentsmentioning

confidence: 99%

Blexisma2: A distributed agent framework for constructing a semantic lexical database based on conceptual vectors

Schwab

Tze

2008

2008 First International Conference on Distributed Framework and Applications

Self Cite

View full text Add to dashboard Cite

In the framework of meaning representation in Natural Language Processing (NLP), we aim to develop a system that can be used for heterogeneous applications such as Machine Translation, Information Retrieval or Lexical Access. This system is based on six hypotheses which concern meaning representation and acquisition. In this paper, we discuss the related hypotheses that motivate the construction of a such system and how these hypotheses, together with NLP software engineering concerns, led us to conceive a distributed m uUi-agent system for our goals. We present Blexisma2, a distributed multi-agent system for NLP, its conceptual properties, and an exam pie of inter-agent collaboration. The system is currently being tested on a Grid computing environment.

show abstract

Section: Towards a Society Of Agentsmentioning

confidence: 99%

Blexisma2: A distributed agent framework for constructing a semantic lexical database based on conceptual vectors

Schwab

Tze

2008

2008 First International Conference on Distributed Framework and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Kinds and Properties Of Semantic Cognitive Mapsmentioning

confidence: 99%

“…How can one introduce synonymy and antonymy into the geometrical framework outlined above in which only the notion of dissimilarity is initially assumed to be represented by distances? To the best of our knowledge, this is an open problem [13].Another issue concerns the semantics of the coordinates of the ambient space in which the map image lives. A recognized limitation of LSA and related approaches is that semantic dimensions cannot be clearly identified: ''The typical feature of LSA is that dimensions are latent.…”

mentioning

confidence: 99%

Toward a semantic general theory of everything

Samsonovich¹,

Goldin²,

Ascoli³

2009

Complexity

View full text Add to dashboard Cite

The notion of a universal semantic cognitive map is introduced as a general indexing space for semantics, useful to reduce semantic relations to geometric and topological relations. As a first step in designing the concept, the notion of semantics is operationalized in terms of human subjective experience and is related to the concept of spatial position. Then synonymy and antonymy are introduced in geometrical terms. Further analysis building on previous studies of the authors indicates that the universal semantic cognitive map should be locally low-dimensional. This essay ends with a proposal to develop a metric system for subjective experiences based on the outlined approach. We conclude that a computationally defined universal semantic cognitive map is a necessary tool for the emerging new science of the mind: a scientific paradigm that includes subjective experience as an object of study.2009 Wiley Periodicals, Inc. Complexity 15: 12-18, 2010 INTRODUCTION I magine that in a remote future all meaningful information is laid out in some abstract space based on its semantics. Let us call this space the universal semantic space, and the entire distribution of available chunks* of information in it (which may look like stars in the galaxy on the cover illustration) the universal semantic cognitive map. The idea may sound intuitively familiar, as spatial analogies play a prominent role in human cognition and memory [1,2]. However, the notion of a universal semantic cognitive map goes beyond mere indexing or analogy. The map in and by itself can be used as a language and a complete representation of all information that is ''indexed'' on it. Indeed, if each precise map location uniquely determines the associated meaning then, literally, one point of this map should be worth thousands of words. This representation of information, however, would make no practical sense, if map coordinates were assigned to chunks at random. Instead, as for a road atlas, a useful map would enable semantic inferences by virtue of geometric and topological inferences. Therefore, we assume that: If this hypothetical construct is ever to materialize, it will in fact constitute a General Theory of Everything, once a dream of a great-grandfather of Ijon Tichy (a Stanislaw Lem's character). In comparison, we have a rather modest ambition to outline a more precise notion of this challenge from epistemological and mathematical perspectives. In this essay, we first address the critical question of how to measure semantics practically. Next, we introduce key distinctions and definitions of semantic maps. Then, we illustrate these concepts with a simplified example. Finally, we end with a discussion of the potential impact that semantic map may have on the evolution of science and the progress of humankind. COGNITIVE-PSYCHOLOGICAL AND COGNITIVE-NEUROSCIENTIFIC UNDERPINNINGSIn this work, we treat semantics as potential experience of a human subject. In general, the notion of semantics and its definition have been a subject of perpetual philosoph...

show abstract

“…As an example, we expose only the 'complementary' antonymy proposed by [20]: The same method is used for the other types. Complementary antonyms are couples like event/unevent, presence/absence.…”

Section: Two Lexical Items Are In Antonymy Relation If There Is a Symmentioning

confidence: 99%

“…The vector approach is completely at the at the opposite. Offering very easily thematic association, it allows many fine-grained synonymy [7] and antonymy [20] functions to be defined and implemented, but is unable to differentiate or to valid the existence of hyperonymous relations.…”

Section: Introductionmentioning

confidence: 99%