scispace - formally typeset
Search or ask a question
Topic

Semantic similarity

About: Semantic similarity is a research topic. Over the lifetime, 14605 publications have been published within this topic receiving 364659 citations. The topic is also known as: semantic relatedness.


Papers
More filters
Proceedings ArticleDOI
18 Apr 2006
TL;DR: This work proposes an alternate approach for associating semantic information to 3D worlds based on the integration of two web standards: the X3D language and the semantic web, characterized by the definition of scene-independent ontologies and by the defined semantic zones that complement the role of semantic objects for giving a complete description of the environment.
Abstract: While the number of virtual environments available on the net is constantly increasing, most of them are composed by a wide number of low-level geometric objects that lack any semantic description. Such situation prevents advanced uses of the data contained inside the environments, such as selection and extraction of semantic objects or advanced queries that refer to high-level properties of the environment. Recently some attempts have been performed in order to annotate 3D environments using the descriptive capabilities of MPEG-7 standard. While the solutions proposed are interesting, there are still a number of issues to be solved, including the definition of scene-independent ontologies that can be useful in different situations (e.g., 3D world validation, semantic search through a set of worlds, etc.).This work proposes an alternate approach for associating semantic information to 3D worlds based on the integration of two web standards: the X3D language and the semantic web. The approach is characterized also by the definition of scene-independent ontologies and by the definition of semantic zones that complement the role of semantic objects for giving a complete description of the environment.In order to show the potentialities of such approach the paper will illustrate an application scenario characterized by the extraction of the semantic information from an X3D document and the associated ontology for generating a high-level and multilevel textual description of a tour through the 3D environment described by them.

110 citations

Proceedings ArticleDOI
01 Jul 2017
TL;DR: In this article, the role of semantics in zero-shot learning is considered and the effectiveness of previous approaches is analyzed according to the form of supervision provided, while some learn semantics independently, others only supervise the semantic subspace explained by training classes.
Abstract: The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses this issue but leaves part of the semantic space unsupervised. This complementarity is exploited in a new convolutional neural network (CNN) framework, which proposes the use of semantics as constraints for recognition. Although a CNN trained for classification has no transfer ability, this can be encouraged by learning an hidden semantic layer together with a semantic code for classification. Two forms of semantic constraints are then introduced. The first is a loss-based regularizer that introduces a generalization constraint on each semantic predictor. The second is a codeword regularizer that favors semantic-to-class mappings consistent with prior semantic knowledge while allowing these to be learned from data. Significant improvements over the state-of-the-art are achieved on several datasets.

110 citations

Proceedings ArticleDOI
01 Jun 2014
TL;DR: In a quantitative evaluation on the task of judging geographically informed semantic similarity between representations learned from 1.1 billion words of geo-located tweets, the joint model outperforms comparable independent models that learn meaning in isolation.
Abstract: We introduce a model for incorporating contextual information (such as geography) in learning vector-space representations of situated language. In contrast to approaches to multimodal representation learning that have used properties of the object being described (such as its color), our model includes information about the subject (i.e., the speaker), allowing us to learn the contours of a word’s meaning that are shaped by the context in which it is uttered. In a quantitative evaluation on the task of judging geographically informed semantic similarity between representations learned from 1.1 billion words of geo-located tweets, our joint model outperforms comparable independent models that learn meaning in isolation.

110 citations

Patent
07 Oct 2008
TL;DR: In this article, a plurality of corresponding pair similarity score values according to a first and at least a second classifier using electronic information sources is calculated to provide the overall semantic similarity score value between pairs of named entities in a text corpus.
Abstract: An overall semantic similarity score value between pairs of named entities in a text corpus is obtained by calculating for at least one pair of named entities a plurality of corresponding pair similarity score values according to a first and at least a second classifier using electronic information sources. Each pair similarity score value of the pair of named entities per classifier is normalized by calculating a rank list per classifier, for example, for each named entity. The rank list holds each pair of named entities of the text corpus, wherein a rank of each pair of named entities within the rank list reflects the respective pair similarity score value. Further an arithmetic mean of the normalized pair similarity score value of each pair of named entities is calculated to provide the overall semantic similarity score value.

110 citations


Network Information
Related Topics (5)
Web page
50.3K papers, 975.1K citations
84% related
Graph (abstract data type)
69.9K papers, 1.2M citations
84% related
Unsupervised learning
22.7K papers, 1M citations
83% related
Feature vector
48.8K papers, 954.4K citations
83% related
Web service
57.6K papers, 989K citations
82% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023202
2022522
2021641
2020837
2019866
2018787