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
Journal ArticleDOI
TL;DR: It will be argued that the evidence supports a theory of semantic memory that represents meaning in a continuum of levels of meaning from the most specific and Context-bound to the most generalisable and context-free.
Abstract: This paper presents evidence that the breakdown of semantic memory in semantic dementia reveals the influence of two properties of script theory (Schank, 1982; Schank & Abelson, 1977). First, the physical and personal context of specific scripts supports meaning for words, objects, and locations that are involved in the script. Second, meaning is updated or transformed by a dynamic memory system that learns continuously from personal experience. In severe cases, semantic dementia exposes the basic level of this learning system from which all knowledge normally develops. It will be argued that the evidence supports a theory of semantic memory that represents meaning in a continuum of levels of meaning from the most specific and context-bound to the most generalisable and context-free. This contrasts with current theories of semantic memory that represent meaning as a collection of abstracted properties entirely removed from the context of events and activities.

81 citations

Journal ArticleDOI
TL;DR: A new method for identifying the semantic orientation of subjective terms to perform sentiment analysis that is based on a novel semantic orientation representation model called S-HAL (Sentiment Hyperspace Analogue to Language).
Abstract: Sentiment analysis continues to be a most important research problem due to its abundant applications. Identifying the semantic orientation of subjective terms (words or phrases) is a fundamental task for sentiment analysis. In this paper, we propose a new method for identifying the semantic orientation of subjective terms to perform sentiment analysis. The method takes a classification approach that is based on a novel semantic orientation representation model called S-HAL (Sentiment Hyperspace Analogue to Language). S-HAL basically produces a set of weighted features based on surrounding words, and characterizes the semantic orientation information of words via a specific feature space. Because the method incorporates the idea underlying HAL and the hypothesis verified by the method of semantic orientation inference from pointwise mutual information (SO-PMI), it can quickly and accurately identify the semantic orientation of terms without the use of an Internet search engine. The results of an empirical evaluation show that our method outperforms other known methods.

81 citations

Journal ArticleDOI
TL;DR: A memory model is described that creates semantic representations for words that are similar in form to those created by LSA, but instead of applying dimension reduction, the model builds the representations by using a retrieval mechanism from a well-known account of episodic memory.
Abstract: Latent semantic analysis (LSA) is a model of knowledge representation for words. It works by applying dimension reduction to local co-occurrence data from a large collection of documents after performing singular value decomposition on it. When the reduction is applied, the system forms condensed representations for the words that incorporate higher order associations. The higher order associations are primarily responsible for any semantic similarity between words in LSA. In this article, a memory model is described that creates semantic representations for words that are similar in form to those created by LSA. However, instead of applying dimension reduction, the model builds the representations by using a retrieval mechanism from a well-known account of episodic memory.

81 citations

Proceedings ArticleDOI
20 Apr 2009
TL;DR: This work proposes a relational similarity measure, using a Web search engine, to compute the similarity between semantic relations implied by two pairs of words, and evaluates the proposed method in two tasks: classifying semantic relations between named entities, and solving word-analogy questions.
Abstract: Measuring the similarity between semantic relations that hold among entities is an important and necessary step in various Web related tasks such as relation extraction, information retrieval and analogy detection. For example, consider the case in which a person knows a pair of entities (e.g. Google, YouTube), between which a particular relation holds (e.g. acquisition). The person is interested in retrieving other such pairs with similar relations (e.g. Microsoft, Powerset). Existing keyword-based search engines cannot be applied directly in this case because, in keyword-based search, the goal is to retrieve documents that are relevant to the words used in a query -- not necessarily to the relations implied by a pair of words. We propose a relational similarity measure, using a Web search engine, to compute the similarity between semantic relations implied by two pairs of words. Our method has three components: representing the various semantic relations that exist between a pair of words using automatically extracted lexical patterns, clustering the extracted lexical patterns to identify the different patterns that express a particular semantic relation, and measuring the similarity between semantic relations using a metric learning approach. We evaluate the proposed method in two tasks: classifying semantic relations between named entities, and solving word-analogy questions. The proposed method outperforms all baselines in a relation classification task with a statistically significant average precision score of 0.74. Moreover, it reduces the time taken by Latent Relational Analysis to process 374 word-analogy questions from 9 days to less than 6 hours, with an SAT score of 51%.

80 citations

Journal ArticleDOI
S. Kumar1
TL;DR: A computer procedure to reorganize indexing vocabularies is described and a measure of the semantic association between index terms can be determined from the structural relationships which the terms exhibit by their relative positions in the system.
Abstract: A computer procedure to reorganize indexing vocabularies is described. Index terms are drawn from the vocabulary of a structured indexing system and may consist of single words, collections of words, or syntactic phrases. The basic idea is that a measure of the semantic association between index terms can be determined from the structural relationships which the terms exhibit by their relative positions in the system. The association measure, which is based on a priori (preassigned) semantic relationships between terms, rather than their co-occurrence in a document corpus, is then used for grouping index terms into clusters or concepts. Some results of an experimental investigation are presented. K E Y WORDS AND PHRASES: information, retrieval, clustering,

80 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