Search results for "latent semantic analysis"
showing 10 items of 40 documents
Image classification based on 2D feature motifs
2013
The classification of raw data often involves the problem of selecting the appropriate set of features to represent the input data. In general, various features can be extracted from the input dataset, but only some of them are actually relevant for the classification process. Since relevant features are often unknown in real-world problems, many candidate features are usually introduced. This degrades both the speed and the predictive accuracy of the classifier due to the presence of redundancy in the candidate feature set. In this paper, we study the capability of a special class of motifs previously introduced in the literature, i.e. 2D irredundant motifs, when they are exploited as feat…
Semantics driven interaction using natural language in students tutoring
2007
The aim of this work is to introduce a semantic integration between an ontology and a chatbot in an Intelligent Tutoring Systems (ITS) to interact with students using natural language. The interaction process is driven by the use of a purposely defined ontology. In the ontology two types of conceptual relations are defined. Besides the usual relations, which are used to define the domain's structure, another type of relation is used to define the navigation schema inside the ontology according to the need of managing uncertainty. Uncertainty level is related to student knowledge level about the involved concepts. In this work we propose an ITS for the Java programming language called TutorJ…
A word prediction methodology for automatic sentence completion
2015
Word prediction generally relies on n-grams occurrence statistics, which may have huge data storage requirements and does not take into account the general meaning of the text. We propose an alternative methodology, based on Latent Semantic Analysis, to address these issues. An asymmetric Word-Word frequency matrix is employed to achieve higher scalability with large training datasets than the classic Word-Document approach. We propose a function for scoring candidate terms for the missing word in a sentence. We show how this function approximates the probability of occurrence of a given candidate word. Experimental results show that the proposed approach outperforms non neural network lang…
Sentence Induced Transformations in Conceptual Spaces
2008
The proposed work illustrates how "primitive concepts" can be automatically induced from a text corpus. The primitive concepts are identified by the orthonormal axis of a "conceptual" space induced by a methodology inspired to the latent semantic analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the "conceptual"space. The rotations, triggered by the sequence of words composing the sentence and realized by means of geometric algebra rotors, allow to highlight "conceptual" relations that can arise among the primitive concepts.
The Use of Latent Semantic Analysis in the Positive Psychology: A Comparison with Twitter Posts
2017
In the last decade, the positive psychology and specifically the 'Positive Youth Development' (PYD) give efforts to positive aspect and strength that performance as protective factors of adjustment problems and psycho-social well-being, such as courage. To better understand the definition of courage in Italian context, 1199 participants were involved in the present study and we asked them to answer to the following question "Courage is...". The participant's definitions of courage were analyzed with the Latent Semantic Analysis (LSA), in order to study the "fundamental concepts" arising from the population. An analogous comparison with Twitter posts has been also carried out.
A combined semantic-syntactic sentence analysis for students assessment
2010
TutorJ is an Intelligent Tutoring System able to fulfill the requests of a student with a learning path inside didactical materials. To this aim, it must assess the level of training of the learner. In the first version of TutorJ this goal was reached through a conversational agent whose linguistic interaction enriched by a LSA-based text analysis. This approach suffers from the limitations of LSA as a bag-of- words approach. Next, morphosyntactic comparison of sentences' structures was implemented. In this paper we present a new version of the assessment procedure involving both semantic, and morphosyntactic analysis user's sentences.
Knowledge Representation in Empathic Robots-Rappresentazione della conoscenza in robot empatici
2011
In questo articolo si illustra l'architettura cognitiva di un robot umanoide basato sul paradigma della Latent Semantic Analysis (LSA). L'approccio LSA consente la creazione e l'utilizzo di un spazio concettuale multi-dimensionale e data driven. Questo paradigma è un passo verso la simulazione di un comportamento emotivo di un robot che interagisce con gli umani. L'architettura è organizzata in tre aree principali: Subconcettuale, emotivo e comportamentale. La prima area elabora i dati percettivi provenienti dai sensori. La seconda area è lo "spazio concettuale di stati emotivi" che costituisce la rappresentazione sub-simbolica di emozioni. L'ultima area attiva un comportamento semantico la…
Latent Semantic Description of Iconic Scenes
2005
It is proposed an approach for the automatic description of scenes using a LSA–like technique. The described scenes are composed by a set of elements that can be geometric forms or iconic representation of objects. Every icon is characterized by a set of attributes like shape, colour and position. Each scene is related to a set of sentences describing their content. The proposed approach builds a data driven vector semantic space where the scenes and the sentences are mapped. A new scene can be mapped in this created space accordingly to a suitable metric. Preliminary experimental results show the effectiveness of the procedure.
A Geometric Algebra Based Distributional Model to Encode Sentences Semantics
2013
Word space models are used to encode the semantics of natural language elements by means of high dimensional vectors [23]. Latent Semantic Analysis (LSA) methodology [15] is well known and widely used for its generalization properties. Despite of its good performance in several applications, the model induced by LSA ignores dynamic changes in sentences meaning that depend on the order of the words, because it is based on a bag of words analysis. In this chapter we present a technique that exploits LSA-based semantic spaces and geometric algebra in order to obtain a sub-symbolic encoding of sentences taking into account the words sequence in the sentence. © 2014 Springer-Verlag Berlin Heidel…
Sub-symbolic Encoding of Words
2003
A new methodology for sub-symbolic semantic encoding of words is presented. The methodology uses the WordNet lexical database and an ad hoc modified Sammon algorithm to associate a vector to each word in a semantic n-space. All words have been grouped according to the WordNet lexicographers’ files classification criteria: these groups have been called lexical sets. The word vector is composed by two parts: the first one, takes into account the belonging of the word to one of these lexical sets; the second one is related to the meaning of the word and it is responsible for distinguishing the word among the other ones of the same lexical set. The application of the proposed technique over all…