Semantic Space Model Research Articles

Correction to: Measuring the semantic headedness of English blends with token-based semantic vector space modeling: a corpus-based study

Correction to: Measuring the semantic headedness of English blends with token-based semantic vector space modeling: a corpus-based study

Measuring the semantic headedness of English blends with token-based semantic vector space modeling: a corpus-based study

Abstract This article analyzes the semantic headedness of English blends with distributional semantics methods. The semantic head of a blend is the source word that transfers its semantic information to the blend as a whole. For example, a sitcom is a kind of comedy. But is FedEx a kind of express, and is wi-fi a kind of fidelity? We use corpus data and token-based semantic vector space modeling in order to address these questions. Specifically, we investigate whether Plag’s ternary division of endocentric, exocentric, and coordinative compounds based on semantic headedness can also be applied to English blends, and whether the general tendency of semantic right-headedness can be observed for all three subtypes. We analyze a dataset of fifty-five blends and their respective source words, using data from the Corpus of Contemporary American English and the English Web Corpus 2021. We measure the degree of semantic similarity between each blend and its two source words. The results show that for most endocentric blends, the hypothesis of semantic right-headedness holds true. At the same time, exocentric blends and coordinative blends are shown to behave differently. We conclude that Plag’s classification offers a useful point of departure for the semantic analysis of blends and that distributional semantics methods can provide new insights into their semantic behavior.

Overlapping representations of observed actions and action-related features.

The lateral occipitotemporal cortex (LOTC) has been shown to capture the representational structure of a smaller range of actions. In the current study, we carried out an fMRI experiment in which we presented human participants with images depicting 100 different actions and used representational similarity analysis (RSA) to determine which brain regions capture the semantic action space established using judgments of action similarity. Moreover, to determine the contribution of a wide range of action-related features to the neural representation of the semantic action space we constructed an action feature model on the basis of ratings of 44 different features. We found that the semantic action space model and the action feature model are best captured by overlapping activation patterns in bilateral LOTC and ventral occipitotemporal cortex (VOTC). An RSA on eight dimensions resulting from principal component analysis carried out on the action feature model revealed partly overlapping representations within bilateral LOTC, VOTC, and the parietal lobe. Our results suggest spatially overlapping representations of the semantic action space of a wide range of actions and the corresponding action-related features. Together, our results add to our understanding of the kind of representations along the LOTC that support action understanding.

Assessing coherence through linguistic connectives: Analysis of speech in patients with schizophrenia-spectrum disorders.

Incoherent speech is a core diagnostic symptom of schizophrenia-spectrum disorders (SSD) that can be studied using semantic space models. Since linguistic connectives signal relations between words, they and their surrounding words might represent linguistic loci to detect unusual coherence in speech. Therefore, we investigated whether connectives' measures are useful to assess incoherent speech in SSD. Connectives and their surrounding words were extracted from transcripts of spontaneous speech of 50 SSD-patients and 50 control participants. Using word2vec, two different cosine similarities were calculated: those of connectives and their surrounding words (connectives-related similarity), and those of free-of-connectives words-chunks (non-connectives similarity). Differences between groups in proportion of five types of connectives were assessed using generalized logistic models, and connectives-related similarity was analyzed through non-parametric multivariate analysis of variance. These features were evaluated in classification tasks to differentiate between groups. SSD-patients used less contingency (e.g., because) (p=.008) and multiclass connectives (e.g., as) (p<.001) than control participants. SSD-patients had higher minimum similarity of multiclass (adj-p=.04) and temporality connectives (e.g., after) (adj-p<.001), narrower similarity-range of expansion (e.g., and) (adj-p=.002) and multiclass connectives (adj-p=.04), and lower maximum similarity of expansion connectives (adj-p=.005). Using connectives' features alone, SSD-patients and controls could be distinguished with 85% accuracy. Our results show that SSD-speech can be distinguished from speech of control participants with high accuracy, based solely on connectives' features. We conclude that including connectives could strengthen computational models to categorize SSD.

Bigram semantic distance as an index of continuous semantic flow in natural language: Theory, tools, and applications.

Much of our understanding of word meaning has been informed through studies of single words. High-dimensional semantic space models have recently proven instrumental in elucidating connections between words. Here we show how bigram semantic distance can yield novel insights into conceptual cohesion and topic flow when computed over continuous language samples. For example, "Cats drink milk" is comprised of an ordered vector of bigrams (cat-drink, drink-milk). Each of these bigrams has a unique semantic distance. These distances in turn may provide a metric of dispersion or the flow of concepts as language unfolds. We offer an R-package ("semdistflow") that transforms any user-specified language transcript into a vector of ordered bigrams, appending two metrics of semantic distance to each pair. We validated these distance metrics on a continuous stream of simulated verbal fluency data assigning predicted switch markers between alternating semantic clusters (animals, musical instruments, fruit). We then generated bigram distance norms on a large sample of text and demonstrated applications of the technique to a classic work of short fiction, To Build a Fire (London, 1908). In one application, we showed that bigrams spanning sentence boundaries are punctuated by jumps in the semantic distance. We discuss the promise of this technique for characterizing semantic processing in real-world narratives and for bridging findings at the single word level with macroscale discourse analyses. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Extracting Place Functionality From Crowdsourced Textual Data Using Semantic Space Modeling

Extracting Place Functionality From Crowdsourced Textual Data Using Semantic Space Modeling

Gender Asymmetry of Visegrád Group Languages as Reflected by Word Embeddings

Abstract Today, word embeddings have become a standard method in natural language processing, largely due to the availability of large language corpora. The models effectively reflect the semantic relationships between words without any additional linguistic input. Recently, more emphasis has been placed on interpreting the seemingly discriminatory results of some queries, with the goal of de-biasing language models. However, if we consider the vector space to be a reasonably valid model of a linguistic semantic space, does not the asymmetry and subsequent discrimination in word embeddings reflect the (average) discriminatory tendencies inherent in the language? This article explores word embedding models for the Visegrád group languages and we apply basic vector arithmetic to demonstrate the basic language asymmetry present in the models. It is well known that in English models, vector transfers result in eerily accurate predictions when swapping genders (the famous king – man + woman = queen), but these transfers also result in rather uncomplimentary roles for certain occupations (doctor – man + woman = nurse, or computer programmer – man + woman = homemaker). The article explores similar transfers in models of V4 languages – Slovak, Czech, Polish, and Hungarian. With Hungarian gender neutrality, Polish strong generic masculine, and close parallels between Slovak and Czech, we hope to uncover interesting similarities and differences in gender asymmetry in these languages, based on real language data.

A knowledge recommendation approach in design for multi-material 4D printing based on semantic similarity vector space model and case-based reasoning

4D printing refers to a breakthrough technology combining additive manufacturing (AM) and smart materials (SMs) under the effect of an energy stimulation. From the numerous experiments proposed in the literature, which highlight the broad spectrum of shape- and/or property-changing capacities, an emerging research interest is to tackle 4D printing from a design perspective. The so-called design for 4D printing requires rethinking well-established models, methods, and tools to develop innovative devices with changing capacities. It is particularly suitable to focus on the computational design synthesis where decisions on AM techniques and SMs selection have an important influence on the part geometry and materials distribution. Previous research work has developed an ontology for capturing multiple perspective knowledge related to SMs, stimuli, AM, and product design. However, the construction of a complex and interdisciplinary knowledge base is not sufficient and requires knowledge reuse/recommendation mechanisms for guiding designers and engineers. Therefore, the article aims to propose a knowledge recommendation approach in computational design for 4D printing with a semantic similarity vector space model. A specific emphasis is made on multi-material 4D printing where recommendations are needed to determine active and passive materials’ distributions for achieving the desired shape change. An implementation of the approach in a computer-aided design plugin is described and illustrative cases from the literature are introduced to demonstrate its applicability.

A semantic and intelligent focused crawler based on semantic vector space model and membrane computing optimization algorithm

A semantic and intelligent focused crawler based on semantic vector space model and membrane computing optimization algorithm

A focused crawler based on semantic disambiguation vector space model

The focused crawler grabs continuously web pages related to the given topic according to priorities of unvisited hyperlinks. In many previous studies, the focused crawlers predict priorities of unvisited hyperlinks based on the text similarity models. However, the representation terms of the web page ignore the phenomenon of polysemy, and the topic similarity of the text cannot combine the cosine similarity and the semantic similarity effectively. To address these problems, this paper proposes a focused crawler based on semantic disambiguation vector space model (SDVSM). The SDVSM method combines the semantic disambiguation graph (SDG) and the semantic vector space model (SVSM). The SDG is used to remove the ambiguation terms irrelevant to the given topic from representation terms of retrieved web pages. The SVSM is used to calculate the topic similarity of the text by constructing text and topic semantic vectors based on TF × IDF weights of terms and semantic similarities between terms. The experiment results indicate that the SDVSM method can improve the performance of the focused crawler by comparing different evaluation indicators for four focused crawlers. In conclusion, the proposed method can make the focused crawler grab the higher quality and more quantity web pages related to the given topic from the Internet.

Indoor Positioning and Navigation Model Based on Semantic Grid

Traditional GPS positioning technology cannot be used in indoor space. With the development of the new positioning technology and the Internet of things, the indoor mobile object positioning and navigation model have been the focus of the relevant research institutions at home and abroad. Based on this, indoor positioning technology was studied starting from Wi-Fi, RFID, and iBeacon technology in this paper. However, the accuracy of indoor positioning and navigation needs to be further improved. This paper presents a semantic space model based on artificial intelligence technology, through semantic pattern matching, semantic concept extension, semantic reasoning and semantic mapping, and interior semantic localization is realized. The indoor semantic network and indoor grid navigation model are constructed, and the indoor semantic path is modeled from time, location, user, and congestion. At the same time, the improved Term Frequency-Inverse Document Frequency is combined with the Hidden Markov Model to improve the accuracy of matching the stay area with the most likely location to visit and improve the accuracy of semantic annotation. It was found that the research on the indoor positioning and navigation model based on the semantic grid can realize the uniform expression of the complex spatial semantics of the theme, geometry, connectivity, and distance, which can promote the development of indoor positioning and navigation.

Comparison of Latent Semantic Analysis and Vector Space Model for Automatic Identification of Competent Reviewers to Evaluate Papers

The assignment of reviewers to papers is one of the most important and challenging tasks in organizing scientific events. A major part of it is the correct identification of proper reviewers. This article presents a series of experiments aiming to test whether the latent semantic analysis (LSA) could be reliably used to identify competent reviewers to evaluate submitted papers. It also compares the performance of the LSA, the vector space model (VSM) and the method of explicit document description by a taxonomy of keywords, in computing accurate similarity factors between papers and reviewers. All the three methods share the same input datasets, taken from real-life conferences and the produced paper-reviewer similarities are evaluated with the same evaluation methods, allowing a fair and objective comparison between them. Experimental results show that in most cases LSA outperforms VSM and could even slightly outperform the explicit document description by a taxonomy of keywords, if the term-document matrix is composed of TF-IDF values, rather than the raw number of term occurrences.

A Tensor Space Model-Based Deep Neural Network for Text Classification

Most text classification systems use machine learning algorithms; among these, naïve Bayes and support vector machine algorithms adapted to handle text data afford reasonable performance. Recently, given developments in deep learning technology, several scholars have used deep neural networks (recurrent and convolutional neural networks) to improve text classification. However, deep learning-based text classification has not greatly improved performance compared to that of conventional algorithms. This is because a textual document is essentially expressed as a vector (only), albeit with word dimensions, which compromises the inherent semantic information, even if the vector is (appropriately) transformed to add conceptual information. To solve this ‘loss of term senses’ problem, we develop a concept-driven deep neural network based upon our semantic tensor space model. The semantic tensor used for text representation features a dependency between the term and the concept; we use this to develop three deep neural networks for text classification. We perform experiments using three standard document corpora, and we show that our proposed methods are superior to both traditional and more recent learning methods.

Semantics in High-Dimensional Space.

Geometric models are used for modelling meaning in various semantic-space models. They are seductive in their simplicity and their imaginative qualities, and for that reason, their metaphorical power risks leading our intuitions astray: human intuition works well in a three-dimensional world but is overwhelmed by higher dimensionalities. This note is intended to warn about some practical pitfalls of using high-dimensional geometric representation as a knowledge representation and a memory model—challenges that can be met by informed design of the representation and its application.

Language disorder as a marker for schizophrenia.

A language disorder is a significant symptom of schizophrenia. A psychiatrist can find this disorder when interviews with a patient. Screening and diagnosis in patients with schizophrenia alone rely heavily on interviews conducted on patients and any instructions captured from patients both verbally and nonverbally. A psychiatrist can also analyze the language aspects in schizophrenia from a language level perspective ranging from phonetic to pragmatic. This analysis paves the way for the process of interference detection since the prodromal phase. Language disorder in schizophrenia is often associated with impaired thinking processes. However, with the development of science and technology today, there is an objective and quantitative method of computational analysis of language through the Natural Language Processing process with a semantic space model that allows a psychiatrist to learn aspects of the human language process, especially in semantic and pragmatic aspects. The review provides a groundbreaking proposal for biomarkers for schizophrenia that have not been available so far through the assessment of language disorders in patients with schizophrenia. Objective and accurate detection of language disorders in schizophrenia can be a modality for psychiatrists to screen, make diagnoses, determine prognosis, evaluate therapies, and monitor recurrence using existing technology media.

Semantic Linkages of Obsessions From an International Obsessive-Compulsive Disorder Mobile App Data Set: Big Data Analytics Study.

BackgroundObsessive-compulsive disorder (OCD) is characterized by recurrent intrusive thoughts, urges, or images (obsessions) and repetitive physical or mental behaviors (compulsions). Previous factor analytic and clustering studies suggest the presence of three or four subtypes of OCD symptoms. However, these studies have relied on predefined symptom checklists, which are limited in breadth and may be biased toward researchers’ previous conceptualizations of OCD.ObjectiveIn this study, we examine a large data set of freely reported obsession symptoms obtained from an OCD mobile app as an alternative to uncovering potential OCD subtypes. From this, we examine data-driven clusters of obsessions based on their latent semantic relationships in the English language using word embeddings.MethodsWe extracted free-text entry words describing obsessions in a large sample of users of a mobile app, NOCD. Semantic vector space modeling was applied using the Global Vectors for Word Representation algorithm. A domain-specific extension, Mittens, was also applied to enhance the corpus with OCD-specific words. The resulting representations provided linear substructures of the word vector in a 100-dimensional space. We applied principal component analysis to the 100-dimensional vector representation of the most frequent words, followed by k-means clustering to obtain clusters of related words.ResultsWe obtained 7001 unique words representing obsessions from 25,369 individuals. Heuristics for determining the optimal number of clusters pointed to a three-cluster solution for grouping subtypes of OCD. The first had themes relating to relationship and just-right; the second had themes relating to doubt and checking; and the third had themes relating to contamination, somatic, physical harm, and sexual harm. All three clusters showed close semantic relationships with each other in the central area of convergence, with themes relating to harm. An equal-sized split-sample analysis across individuals and a split-sample analysis over time both showed overall stable cluster solutions. Words in the third cluster were the most frequently occurring words, followed by words in the first cluster.ConclusionsThe clustering of naturally acquired obsessional words resulted in three major groupings of semantic themes, which partially overlapped with predefined checklists from previous studies. Furthermore, the closeness of the overall embedded relationships across clusters and their central convergence on harm suggests that, at least at the level of self-reported obsessional thoughts, most obsessions have close semantic relationships. Harm to self or others may be an underlying organizing theme across many obsessions. Notably, relationship-themed words, not previously included in factor-analytic studies, clustered with just-right words. These novel insights have potential implications for understanding how an apparent multitude of obsessional symptoms are connected by underlying themes. This observation could aid exposure-based treatment approaches and could be used as a conceptual framework for future research.

Discovery Model Based on Analogies for Teaching Computer Programming

Teaching the fundamentals of computer programming in a first course (CS1) is a complex activity for the professor and is also a challenge for them. Nowadays, there are several teaching strategies for dealing with a CS1 at the university, one of which is the use of analogies to support the abstraction process that a student needs to carry for the appropriation of fundamental concepts. This article presents the results of applying a discovery model that allowed for the extraction of patterns, linguistic analysis, textual analytics, and linked data when using analogies for teaching the fundamental concepts of programming by professors in a CS1 in university programs that train software developers. For that reason, a discovery model based on machine learning and text mining was proposed using natural language processing techniques for semantic vector space modeling, distributional semantics, and the generation of synthetic data. The discovery process was carried out using nine supervised learning methods, three unsupervised learning methods, and one semi-supervised learning method involving linguistic analysis techniques, text analytics, and linked data. The main findings showed that professors include keywords, which are part of the technical computer terminology, in the form of verbs in the statement of the analogy and combine them in quantitative contexts with neutral or positive phrases, where numerical examples, cooking recipes, and games were the most used categories. Finally, a structure is proposed for the construction of analogies to teach programming concepts and this was validated by the professors and students.

Frequency-Dependent Cortical Interactions during Semantic Processing: An Electrocorticogram Cross-spectrum Analysis Using a Semantic Space Model.

Convergent evidence has demonstrated that semantics are represented by the interaction between a multimodal semantic hub at the anterior temporal lobe (ATL) and other modality-specific association cortical areas. Electrocorticogram (ECoG) recording with high spatiotemporal resolutions is efficient in evaluating such cortical interactions; however, this has not been a focus of preceding studies. The present study evaluated cortical interactions during picture naming using a novel ECoG cross-spectrum analysis, which was formulated from a computational simulation of neuronal networks and combined with a vector space model of semantics. The results clarified three types of frequency-dependent cortical networks: 1) an earlier-period (0.2-0.8s from stimulus onset) high-gamma-band (90-150Hz) network with a hub at the posterior fusiform gyrus, 2) a later-period (0.4-1.0s) beta-band (15-40Hz) network with multiple hubs at the ventral ATL and posterior middle temporal gyrus, and 3) a pre-articulation theta-band (4-7 Hz) network distributed over widely located cortical regions. These results suggest that frequency-dependent cortical interactions can characterize the underlying processes of semantic cognition, and the beta-band network with a hub at the ventral ATL is especially associated with the formation of semantic representation.

Networks of Autonomous Real-Time Agents in Environments with Counteraction: Features and Components of the Model

A group behavior and control model in a system consisting of autonomous real-world and Internet objects with opposition is considered. The urgency of the problem is due to the growing role of Internet technologies in competition models in economics, politics, computer security, etc. The problem model is analyzed in the context of the Boyd Cycle. The tasks of the cycle phases are formulated, a multi-agent model of the behavior of autonomous objects and the digital twin of the external environment in the control loop is substantiated. The necessity of using the model of a unified semantic knowledge and data space is argued.

A Wikipedia-based semantic tensor space model for text analytics

This paper proposes a third-order tensor space model that represents textual documents, which contains the 'concept' space independently of the 'document' and 'term' spaces. In the vector space model (VSM), a document is represented as a vector in which each dimension corresponds to a term. In contrast, the model described here represents a document as a matrix. Most current text mining algorithms only take vectors as their input, but they suffer from 'term independence' and 'loss of term senses' issues. To overcome these problems, we incorporate the 'concept' as a distinct space in the VSM. For this, it is necessary to produce the concept vector for each term that occurs in a given document, which is related to word sense disambiguation. As an external knowledge source for concept weighting, we employ the Wikipedia Encyclopedia, which has been evaluated as world knowledge and used to improve many text-mining algorithms. Through experiments using two popular document corpora, we demonstrate the superiority of the model in terms of text clustering and text classification.