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 published on a yearly basis
Papers
More filters
07 Nov 2003
TL;DR: A novel image retrieval scheme, CLUster-based rEtrieval of images by unsupervised learning (CLUE), which tackles the semantic gap problem based on a hypothesis: semantically similar images tend to be clustered in some feature space.
Abstract: In a typical content-based image retrieval (CBIR) system, query results are a set of images sorted by feature similarities with respect to the query. However, images with high feature similarities to the query may be very different from the query in terms of semantics. This is known as the semantic gap. We introduce a novel image retrieval scheme, CLUster-based rEtrieval of images by unsupervised learning (CLUE), which tackles the semantic gap problem based on a hypothesis: semantically similar images tend to be clustered in some feature space. CLUE attempts to capture semantic concepts by learning the way that images of the same semantics are similar and retrieving image clusters instead of a set of ordered images. Clustering in CLUE is dynamic. In particular, clusters formed depend on which images are retrieved in response to the query. Therefore, the clusters give the algorithm as well as the users semantic relevant clues as to where to navigate. CLUE is a general approach that can be combined with any real-valued symmetric similarity measure (metric or nonmetric). Thus it may be embedded in many current CBIR systems. Experimental results based on a database of about 60, 000 images from COREL demonstrate improved performance.
132 citations
01 Dec 1991
TL;DR: To compute thesemantic similarity of classes which utilized fuzzy and incomplete terminological and schema knowledge, the notion ofsemantic relevance is introduced and fuzzy set theory is applied to reason about both terminological knowledge and schemaknowledge.
Abstract: We present an approach to determine the similarity of classes which utilized fuzzy and incomplete terminological knowledge together with schema knowledge. We clearly distinguish between semantic similarity determining the degree of resemblance according to real world semantics, and structural correspondence explaining how classes can actually be interrelated. To compute the semantic similarity we introduce the notion of semantic relevance and apply fuzzy set theory to reason about both terminological knowledge and schema knowledge.
132 citations
Proceedings Article•
01 Jan 2004
TL;DR: A new system is described that enhances Criterion’s capability, by evaluating multiple aspects of coherence in essays, by identifying features of sentences based on semantic similarity measures and discourse structure.
Abstract: Criterion Online Essay Evaluation Service includes a capability that labels sentences in student writing with essay-based discourse elements (e.g., thesis statements). We describe a new system that enhances Criterion’s capability, by evaluating multiple aspects of coherence in essays. This system identifies features of sentences based on semantic similarity measures and discourse structure. A support vector machine uses these features to capture breakdowns in coherence due to relatedness to the essay question and relatedness between discourse elements. Intra-sentential quality is evaluated with rule-based heuristics. Results indicate that the system yields higher performance than a baseline on all three aspects.
131 citations
31 Mar 2009
TL;DR: A new statistical method for detecting and tracking changes in word meaning, based on Latent Semantic Analysis, which allows researchers to make statistical inferences on questions such as whether the meaning of a word changed across time or if a phonetic cluster is associated with a specific meaning.
Abstract: This paper presents a new statistical method for detecting and tracking changes in word meaning, based on Latent Semantic Analysis. By comparing the density of semantic vector clusters this method allows researchers to make statistical inferences on questions such as whether the meaning of a word changed across time or if a phonetic cluster is associated with a specific meaning. Possible applications of this method are then illustrated in tracing the semantic change of 'dog', 'do', and 'deer' in early English and examining and comparing phonaesthemes.
131 citations
13 Jul 2018
TL;DR: This work designs a deep architecture and a pair-wise loss function to preserve the semantic structure of the semantic relationships between points in unsupervised settings, and shows that SSDH significantly outperforms current state-of-the-art methods.
Abstract: Hashing is becoming increasingly popular for approximate nearest neighbor searching in massive databases due to its storage and search efficiency. Recent supervised hashing methods, which usually construct semantic similarity matrices to guide hash code learning using label information, have shown promising results. However, it is relatively difficult to capture and utilize the semantic relationships between points in unsupervised settings. To address this problem, we propose a novel unsupervised deep framework called Semantic Structure-based unsupervised Deep Hashing (SSDH). We first empirically study the deep feature statistics, and find that the distribution of the cosine distance for point pairs can be estimated by two half Gaussian distributions. Based on this observation, we construct the semantic structure by considering points with distances obviously smaller than the others as semantically similar and points with distances obviously larger than the others as semantically dissimilar. We then design a deep architecture and a pair-wise loss function to preserve this semantic structure in Hamming space. Extensive experiments show that SSDH significantly outperforms current state-of-the-art methods.
131 citations