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.

Knowledge representation for syntactic/semantic processing

Abstract: This paper describes the RUS framework for natural language processing, in which a parser incorporating a substantial ATN grammar for English interacts with a semantic interpreter to simultaneously parse and interpret input. The structure of that interaction is discussed, including the roles played by syntactic and semantic knowledge. Several implementations of the RUS framework are currently in use, sharing the same grammar, but differing in the form of their semantic component. One of these, the PSI-KLONE system, is based on a general object-centered knowledge representation system, called KL-ONE. The operation of PSI-KLONE is described, including its use of KL-ONE to support a general inference process called "incremental description refinement." The last section of the paper discusses several important criteria for knowledge representation systems to be used in syntactic and semantic processing.

Information Retrieval by Semantic Similarity

Abstract: Semantic Similarity relates to computing the similarity between conceptually similar but not necessarily lexically similar terms. Typically, semantic similarity is computed by mapping terms to an ontology and by examining their relationships in that ontology. We investigate approaches to computing the semantic similarity between natural language terms (using WordNet as the underlying reference ontology) and between medical terms (using the MeSH ontology of medical and biomedical terms). The most popular semantic similarity methods are implemented and evaluated using WordNet and MeSH. Building upon semantic similarity, we propose the Semantic Similarity based Retrieval Model (SSRM), a novel information retrieval method capable for discovering similarities between documents containing conceptually similar terms. The most effective semantic similarity method is implemented into SSRM. SSRM has been applied in retrieval on OHSUMED (a standard TREC collection available on the Web). The experimental results demonstrated promising performance improvements over classic information retrieval methods utilizing plain lexical matching (e.g., Vector Space Model) and also over state-of-the-art semantic similarity retrieval methods utilizing ontologies.

Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics

Abstract: We construct multi-modal concept representations by concatenating a skip-gram linguistic representation vector with a visual concept representation vector computed using the feature extraction layers of a deep convolutional neural network (CNN) trained on a large labeled object recognition dataset. This transfer learning approach brings a clear performance gain over features based on the traditional bag-of-visual-word approach. Experimental results are reported on the WordSim353 and MEN semantic relatedness evaluation tasks. We use visual features computed using either ImageNet or ESP Game images.

An Empirical Model of Multiword Expression Decomposability

Abstract: This paper presents a construction-inspecific model of multiword expression decomposability based on latent semantic analysis. We use latent semantic analysis to determine the similarity between a multiword expression and its constituent words, and claim that higher similarities indicate greater decomposability. We test the model over English noun-noun compounds and verb-particles, and evaluate its correlation with similarities and hyponymy values in WordNet. Based on mean hyponymy over partitions of data ranked on similarity, we furnish evidence for the calculated similarities being correlated with the semantic relational content of WordNet.