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.

Searching service repositories by combining semantic and ontological matching

Abstract: In this paper, we explore the use of domain-independent and domain-specific ontologies to find matching service descriptions. The domain-independent relationships are derived using an English thesaurus after tokenization and part-of-speech tagging. The domain-specific ontological similarity is derived by an inference on the semantic annotations associated with Web service descriptions. Matches due to the two cues are combined to determine an overall semantic similarity score. By combining multiple cues, we show that better relevancy results can be obtained for service matches from a large repository, than could be obtained using any one cue alone.

A Semantic Similarity Measure for Expressive Description Logics

Abstract: A totally semantic measure is presented which is able to calculate a similarity value between concept descriptions and also between concept description and individual or between individuals expressed in an expressive description logic. It is applicable on symbolic descriptions although it uses a numeric approach for the calculus. Considering that Description Logics stand as the theoretic framework for the ontological knowledge representation and reasoning, the proposed measure can be effectively used for agglomerative and divisional clustering task applied to the semantic web domain.

Spontaneously Reactivated Patterns in Frontal and Temporal Lobe Predict Semantic Clustering during Memory Search

Abstract: Although it is well established that remembering an item will bring to mind memories of other semantically related items ([Bousfield, 1953][1]), the neural basis of this phenomenon is poorly understood. We studied how the similarity relations among items influence their retrieval by analyzing electrocorticographic recordings taken as 46 human neurosurgical patients studied and freely recalled lists of words. We first identified semantic components of neural activity that varied systematically with the meanings of each studied word, as defined by latent semantic analysis ([Landauer and Dumais, 1997][2]). We then examined the dynamics of these semantic components as participants attempted to recall the previously studied words. Our analyses revealed that the semantic components of neural activity were spontaneously reactivated during memory search, just before recall of the studied words. Further, the degree to which neural activity correlated with semantic similarity during recall predicted participants' tendencies to organize the sequences of their responses on the basis of semantic similarity. Thus, our work shows that differences in the neural correlates of semantic information, and how they are reactivated before recall, reveal how individuals organize and retrieve memories of words. [1]: #ref-1 [2]: #ref-24

Procedural semantics for a question-answering machine

Abstract: Simmons has presented a survey of some fifteen experimental question-answering and related systems which have been constructed since 1959. These systems take input questions in natural English (subject to varying constraints) and attempt to answer the questions on the basis of a body of information, called the data base, which is stored inside the computer. This process can be conceptually divided into three phases---syntatic analysis, semantic analysis, and retrieval, as illustrated schematically in Figure 1. The first phase consists of parsing the input sentence into a structure which explicitly represents the grammatical relationships among the words of the sentence. Using this information the second component constructs a representation of the semantic content or "meaning" of the sentence. The remaining phase consists of procedures for either retrieving the answer directly from the data base, or else deducing the answer from information contained in the data base. The dotted lines in the figure represent the possible use of feedback from the later stages to aid in parsing and semantic interpretation.

Semantic integration in text: from ambiguous names to identifiable entities

Abstract: Semantic integration focuses on discovering, representing, and manipulating correspondences between entities in disparate data sources. The topic has been widely studied in the context of structured data, with problems being considered including ontology and schema matching, matching relational tuples, and reconciling inconsistent data values. In recent years, however, semantic integration over text has also received increasing attention. This article studies a key challenge in semantic integration over text: identifying whether different mentions of real-world entities, such as "JFK" and "John Kennedy," within and across natural language text documents, actually represent the same concept.We present a machine-learning study of this problem. The first approach is a discriminative approach--a pairwise local classifier is trained in a supervised way to determine whether two given mentions represent the same real-world entity. This is followed, potentially, by a global clustering algorithm that uses the classifier as its similarity metric. Our second approach is a global generative model, at the heart of which is a view on how documents are generated and how names (of different entity types) are "sprinkled" into them. In its most general form, our model assumes (1) a joint distribution over entities (for example, a document that mentions "President Kennedy" is more likely to mention "Oswald" or "White House" than "Roger Clemens"), and (2) an "author" model that assumes that at least one mention of an entity in a document is easily identifiable and then generates other mentions via (3) an "appearance" model that governs how mentions are transformed from the "representative" mention. We show that both approaches perform very accurately, in the range of 90-95 percent. F1 measure for different entity types, much better than previous approaches to some aspects of this problem. Finally, we discuss how our solution for mention matching in text can be potentially applied to matching relational tuples, as well as to linking entities across databases and text.