Semantic Concepts Research Articles

Attack semantics and collective attacks revisited

In the current paper we re-examine the concepts of attack semantics and collective attacks in abstract argumentation, and examine how these concepts interact with each other. For this, we systematically map the space of possibilities. Starting with standard argumentation frameworks (which consist of a directed graph with nodes and arrows) we briefly state both node semantics and arrow semantics (the latter a.k.a. attack semantics) in both their extensions-based form and labellings-based form. We then proceed with SETAFs (which consist of a directed hypergraph of nodes and arrows, to take into account the notion of collective attacks) and state both node semantics and arrow semantics, in both their extensions-based and labellings-based form. We then show equivalence between the extensions-based and labellings-based form, for node semantics and arrow semantics of AFs, as well as for node semantics and arrow semantics of SETAFs. Moreover, we show equivalence between node semantics and arrow semantics for AFs, and equivalence between node semantics and arrow semantics for SETAFs (with the notable exception of semi-stable). We also provide a novel way of converting a SETAF to an AF such that semantics are preserved, without the use of any “meta arguments”. Although the main part of our work is on the level of abstract argumentation, we do provide an application of our theory on the instantiated level. More specifically, we show that the classical characterisation of Assumption-Based Argumentation (ABA) can be seen as an instantiation based on a SETAF, whereas the contemporary characterisation of ABA can be seen as an instantiation based on a standard AF. Our theory of how to convert a SETAF to an AF can then be used to account for both the similarities and the differences between the classical and contemporary characterisations of ABA. Most prominently, our theory is able to explain the semantic mismatch for semi-stable semantics that arises in the ABA instantiation process.

A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning

To tackle the challenge of recognizing images of unseen attribute-object compositions, Compositional Zero-Shot Learning (CZSL) methods have been previously addressed. However, test images in realistic scenarios may also incorporate other forms of unknown factors, such as novel semantic concepts or novel image styles. As previous CZSL works have overlooked this critical issue, in this research, we first propose the Realistic Compositional Zero-Shot Learning (RCZSL) task which considers the various types of unknown factors in an unified experimental setting. To achieve this, we firstly conduct re-labelling on MIT-States and use the pre-trained generative models to obtain images of various domains. Then the entire dataset is split into a training set and a test set, with the latter containing images of unseen concepts, unseen compositions, unseen domains as well as their combinations. Following this, we show that the visual-semantic relationship changes on unseen images, leading us to construct two dynamic modulators to adapt the visual features and composition prototypes in accordance with the input image. We believe that such a dynamic learning method could effectively alleviate the domain shift problem caused by various types of unknown factors. We conduct extensive experiments on benchmark datasets for both the conventional CZSL setting and the proposed RCZSL setting. The effectiveness of our method has been proven by empirical results, which significantly outperformed both our baseline method and state-of-the-art approaches.

Quality-Diversity Generative Sampling for Learning with Synthetic Data

Generative models can serve as surrogates for some real data sources by creating synthetic training datasets, but in doing so they may transfer biases to downstream tasks. We focus on protecting quality and diversity when generating synthetic training datasets. We propose quality-diversity generative sampling (QDGS), a framework for sampling data uniformly across a user-defined measure space, despite the data coming from a biased generator. QDGS is a model-agnostic framework that uses prompt guidance to optimize a quality objective across measures of diversity for synthetically generated data, without fine-tuning the generative model. Using balanced synthetic datasets generated by QDGS, we first debias classifiers trained on color-biased shape datasets as a proof-of-concept. By applying QDGS to facial data synthesis, we prompt for desired semantic concepts, such as skin tone and age, to create an intersectional dataset with a combined blend of visual features. Leveraging this balanced data for training classifiers improves fairness while maintaining accuracy on facial recognition benchmarks. Code available at: https://github.com/Cylumn/qd-generative-sampling.

NeSyFOLD: A Framework for Interpretable Image Classification

Deep learning models such as CNNs have surpassed human performance in computer vision tasks such as image classi- fication. However, despite their sophistication, these models lack interpretability which can lead to biased outcomes re- flecting existing prejudices in the data. We aim to make pre- dictions made by a CNN interpretable. Hence, we present a novel framework called NeSyFOLD to create a neurosym- bolic (NeSy) model for image classification tasks. The model is a CNN with all layers following the last convolutional layer replaced by a stratified answer set program (ASP) derived from the last layer kernels. The answer set program can be viewed as a rule-set, wherein the truth value of each pred- icate depends on the activation of the corresponding kernel in the CNN. The rule-set serves as a global explanation for the model and is interpretable. We also use our NeSyFOLD framework with a CNN that is trained using a sparse kernel learning technique called Elite BackProp (EBP). This leads to a significant reduction in rule-set size without compromising accuracy or fidelity thus improving scalability of the NeSy model and interpretability of its rule-set. Evaluation is done on datasets with varied complexity and sizes. We also pro- pose a novel algorithm for labelling the predicates in the rule- set with meaningful semantic concept(s) learnt by the CNN. We evaluate the performance of our “semantic labelling algo- rithm” to quantify the efficacy of the semantic labelling for both the NeSy model and the NeSy-EBP model.

Set Prediction Guided by Semantic Concepts for Diverse Video Captioning

Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the intra-set relationship, resulting in low diversity of generated captions. Different from them, we formulate diverse captioning into a semantic-concept-guided set prediction (SCG-SP) problem by fitting the predicted caption set to the ground-truth set, where the set-level relationship is fully captured. Specifically, our set prediction consists of two synergistic tasks, i.e., caption generation and an auxiliary task of concept combination prediction providing extra semantic supervision. Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction. Furthermore, we apply a diversity regularization term on concepts to encourage the model to generate semantically diverse captions with various concept combinations. These two tasks share multiple semantics-specific encodings as input, which are obtained by iterative interaction between visual features and conceptual queries. The correspondence between the generated captions and specific concept combinations further guarantees the interpretability of our model. Extensive experiments on benchmark datasets show that the proposed SCG-SP achieves state-of-the-art (SOTA) performance under both relevance and diversity metrics.

The neural basis of naturalistic semantic and social cognition

Decoding social environments and engaging meaningfully with other people are critical aspects of human cognition. Multiple cognitive systems, including social and semantic cognition, work alongside each other to support these processes. This study investigated shared processing between social and semantic systems using neuroimaging data collected during movie-viewing, which captures the multimodal environment in which social knowledge is exchanged. Semantic and social content from movie events (event-level) and movie transcripts (word-level) were used in parametric modulation analyses to test (1) the degree to which semantic and social information is processed within each respective network and (2) engagement of the same cross-network regions or the same domain-general hub located within the semantic network during semantic and social processing. Semantic word and event-level content engaged the same fronto-temporo-parietal network and a portion of the semantic hub in the anterior temporal lobe (ATL). Social word and event-level content engaged the supplementary motor area and right angular gyrus within the social network, but only social words engaged the domain-general semantic hub in left ATL. There was evidence of shared processing between the social and semantic systems in the dorsolateral portion of right ATL which was engaged by word and event-level semantic and social content. Overlap between the semantic and social word and event results was highly variable within and across participants, with the most consistent loci of overlap occurring in left inferior frontal, bilateral precentral and supramarginal gyri for social and semantic words and in bilateral superior temporal gyrus extending from ATL posteriorly into supramarginal gyri for social and semantic events. These results indicate a complex pattern of shared and distinct regions for social and semantic cognition during naturalistic processing.Protocol registrationThe stage 1 protocol for this Registered Report was accepted in principle on October 11, 2022. The protocol, as accepted by the journal, can be found at: https://doi.org/10.17605/OSF.IO/ACWQY.

Bridging Geospatial and Semantic Worlds: Enhancing Analysis of Place-Based Concepts in GIS

People’s actions and behaviours contribute to the diversity and personality of a space, transforming it into a vibrant and thriving living environment. The main goal of this research is to present a GIS-based framework for assessing places. The framework is constructed based on the idea of conceptual spaces, integrating spatial and semantic concepts inside a geometric structure. The explanation of place-related concepts is achieved via the use of linear programming and convex polytopes. By projecting these concepts into the spatial domain, a strong connection between geographical and semantic space is established. This connection allows a wide range of analytical calculations using geographic information systems to be carried out. The study focuses on the sense of city centre in Tehran, Iran, by employing questionnaires administrated on-site to evaluate the correlation between identified city centres and the participants’ responses. The findings demonstrate a good correlation, as shown by a Pearson correlation value of 0.74 and a rank correlation coefficient of 0.8. Interestingly, the city centres that were selected did not always align with the geographic centre. However, participants still perceived them as city centres. This framework serves as a valuable tool for planners and policymakers, providing a comprehensive understanding of the built environment. By considering both semantic and geographical aspects, the framework emphasises the importance of emotions, memories, and meanings in creating an inclusive environment.

That's not what you said! Semantic constraints on literal speech

According to some philosophers, a sentence's semantics can fail to constitute a complete propositional content, imposing mere constraints on such a content. Recently, Daniel Harris has begun developing a formal constraint semantics. He claims that the semantic values of sentences constrain what speakers can literally say with them—and what hearers can know about what was said. However, that claim is undermined by his conception of semantics as the study of a psychological module. I argue instead that semantic constraints should be understood as properties of public languages.

Atypical semantic cognition in schizotypal personality disorder and borderline personality disorder

ABSTRACT Increased schizotypal traits have previously been associated with atypical semantic cognition in community samples. However, no study has yet examined whether adults diagnosed with schizotypal personality disorder (SPD) display atypical semantic fluency and memory. We hypothesized that 24 adults diagnosed with SPD would name more idiosyncratic words on the semantic fluency task and show decreased semantic recall for animal and fruit category words compared with 29 participants with borderline personality disorder (BPD) and a community sample of 96 age-matched controls. We examined whether atypical semantic cognition was specifically associated with disorganized and eccentric speech and thinking, or more broadly with pathological personality traits and personality functioning. Our main hypothesis was confirmed, as the SPD participants named more idiosyncratic words and recalled fewer semantically related words compared with controls. Surprisingly, participants with BPD likewise named more atypical words compared with controls. More idiosyncratic semantic fluency was associated with more eccentric speech and thinking. Increased idiosyncratic semantic fluency and reduced semantic recall were both coupled to increased detachment and lowered personality functioning, while reduced semantic recall further was related to increased interpersonal problems. Our findings suggest that persons with SPD, and to a lesser degree BPD, show atypical semantic cognition, which is associated with eccentric speech and thinking, and more broadly with impaired personality function, social withdrawal, and emotional flatness. The idiosyncratic semantic cognition may worsen difficulties with social reciprocity seen in SPD and BPD.

Semantics Study of the Indonesian Language Based on Vocabulary Learning in Schools Which is Integrated With Students Discourse Skills: Syllabus Development

This research aims to develop a level 6 syllabus for the Semantics course at the Indonesian Language and Literature Education Study Program. The study materials of the Indonesian Semantics syllabus were developed based on the scope of vocabulary, namely the basic concepts of semantics, meaning analysis, and the use of meaning. The syllabus development model was developed using the ADDIE model steps by adapting its three stages, namely analysis, design, and development. Data were collected by analyzing the curriculum/syllabus/PKPS, analyzing teaching materials, filling out questionnaires to analyze the needs of lecturers and students, analyzing learning activities/methods, syllabus design, and syllabus development and preparation. The syllabus development stage was followed by syllabus expert validation. The results of the data analysis were carried out with a quantitative qualitative description using the results of the pretest and post-test. Through the validation stage of the syllabus product by curriculum experts regarding curriculum aspects (Yes 100%) such as presentation of study materials (Yes 100%) and syllabus completeness (Yes 87.5%). Based on the implementation, the pretest results were obtained with a sample size of 30 students, the highest score was 95 while the lowest score was 55. This pretest data has an average value (mean) of 73 with a median value of 71.5 and a value that often appears (mode) 65. Meanwhile, the variance found was 111.9954 with a standard deviation of 10.58279. While the posttest results were found with the same sample, the highest value was 100 while the lowest value was 70. This posttest data had an average value (mean) of 87 with a median value of 86 and a value that often appears (mode) 90. Meanwhile, the variance found was 111.9954 with a standard deviation of 10.58279. While the posttest results were found with the same sample, the highest score was 100 while the lowest score was 70. This posttest data had an average value (mean) of 87 with a median value of 86 and a value that often appears (mode) 90. Meanwhile, the variance found was 80.39195402 with a standard deviation of 8.966156034. The Semantic Syllabus based on vocabulary learning in schools and integrated with students’ proficiency has been prepared as “very feasible” (96.85%) to be implied in the lecture process in the Indonesian Language and Literature Education Study Program. Thus, it can be stated that the development model of the Indonesian semantic syllabus based on vocabulary language learning in schools and integrated with student literacy applied to students shows a positive effect/improvement.
 Keywords: discourse skills, level 6, linguistic vocabulary, semantics study

Leksem Gajah dalam Peribahasa Melayu Analisis Semantik Inkuisitif

<p><em>A proverb is a sentence that appears with an implied meaning</em><em>.</em><em> The use of elephant elements as a symbol of the condition of Malay Society. The data in this research is data sourced from the Malay Letters Reference Center (PRPM) with elephants as the focus of the data. Meaning in this research uses script semantic analysis, cognitive semantics, and inquisitive semantics. This study was conducted to find out the meaning of the elephant lexeme proverb based on the dictionary meaning, the meaning by linking to societal or social conditions and the meaning by linking to other branches of science. This study produces the meaning of the proverb which means that the elephant is an animal that has a fairly large position among other land animals. The domain that emerges from the results of this analysis is a symbol of the Malay people’s intelligence in choosing symbols based on the habits of the Malay people. The domains that emerge based on inquisitive semantic analysis in the research are (1) the domain of power, (2) the domain of aloofness, and (3) the domain of futility.</em></p>

“All women are like that”: an overview of linguistic deindividualization and dehumanization of women in the incelosphere

Abstract This article provides an overview of linguistic strategies used in the incel community to deindividualize and dehumanize women. Among the most common ways of referring to women there is the use of generic labels (Stacy, Becky), conceptual metaphor (warpig, landwhale) including creative metaphorical morphology (foid, femoid), conceptual metonymy (hole, extrahole), and conceptual metaphtonymy (roastie). The consistent use of such terms within the incelosphere contributes to perpetuating harmful attitudes and potentially even justifying violent and abusive conduct towards women. For this reason, the language of dehumanization in general, and the misogynist discourse of incels in particular, warrants closer attention. This study is carried out within the methodological framework of cognitive semantics and adds to the expanding research on the discourse of the manosphere and the incelosphere.

Insights into Object Semantics: Leveraging Transformer Networks for Advanced Image Captioning.

Image captioning is a technique used to generate descriptive captions for images. Typically, it involves employing a Convolutional Neural Network (CNN) as the encoder to extract visual features, and a decoder model, often based on Recurrent Neural Networks (RNNs), to generate the captions. Recently, the encoder-decoder architecture has witnessed the widespread adoption of the self-attention mechanism. However, this approach faces certain challenges that require further research. One such challenge is that the extracted visual features do not fully exploit the available image information, primarily due to the absence of semantic concepts. This limitation restricts the ability to fully comprehend the content depicted in the image. To address this issue, we present a new image-Transformer-based model boosted with image object semantic representation. Our model incorporates semantic representation in encoder attention, enhancing visual features by integrating instance-level concepts. Additionally, we employ Transformer as the decoder in the language generation module. By doing so, we achieve improved performance in generating accurate and diverse captions. We evaluated the performance of our model on the MS-COCO and novel MACE datasets. The results illustrate that our model aligns with state-of-the-art approaches in terms of caption generation.

Enhancing Industrial Digitalisation through an Adaptable Component for Bridging Semantic Interoperability Gaps

Digital transformation has a great effect on industries but also in the perception of their products with high consequences on society as a whole, as driver for innovation. However, there are still many barriers to the adoption of digital technologies, especially in small and medium-sized enterprises (SMEs). In the present study we propose a new software component that facilitates the adoption of industrial reference architectures (RAs) based on the semantic interoperability concept. Among these RAs, FIWARE has become a key enabler for flexible and resource effective digitalisation of shop floor processes. The proposed software component aims to enable full interoperability between these more widely used technologies and industrial standards and protocols such as OPC UA. As a result, a flexible, open, and adaptable implementation assists the automatic translation of messages from different standards enabling semantic interoperability of shop floor processes. The component aims to enable industrial SMEs to bring current barriers to digitalisation towards a more human-centred, resilient, and sustainable industry and society.

Leksem Lidah dalam Peribahasa Melayu Kajian Semantik Inkuisitif

<p><em>Inquisitive semantic study is a study that aims to find out the deeper and broader meaning of a proverb. Through inquisitive semantic study you can also find out what the implied meaning of a proverb is. The tongue is one of the organs in the human body, it is one of the important organs in the human body, if someone does not have a tongue, it will be difficult to speak and convey things. This research aims to explain the meaning and domain of a proverb which has the object of the tongue based on inquisitive semantic studies. The data collection method used was the reading and note-taking method. The data obtained came from the Malay Literature Reference Center. Data analysis was carried out in three stages, namely the first stage of script semantics, the second stage of cognitive semantics, and the final stage of inquisitive semantics. The research results show that Malay proverbs which have the object of the tongue contain many domains, including the domain of caution, the domain of loss, and the domain of futility.</em></p>

The role of metaphor in creating polysemy complexes in Jordanian Arabic and American English

Most papers written on polysemy focus on sense overlaps and lexical ambiguity, yet studies that explore the possibility of establishing a polysemic complex and explaining how the new interpretations arise through metaphor are almost non-existent in Arabic. This paper aims to explore how metaphor serves to create new concepts as part of polysemic complexes through adopting Dynamic Conceptual Semantics. The target words are bidʒannin [make mad][1] in Jordanian Arabic (JA) and mad in American English (AE). An online questionnaire containing 15 items was sent to forty participants (20 JA speakers and 20 AE speakers) where they were asked to provide the interpretations of the words bidʒannin and mad in contextualized sentences. The AE contextualized instances of mad were collected from Corpus of Contemporary American English (COCA) which generated 5,168 tokens of mad (in the years 2015/2019). The questionnaire results were discussed in a semi-structured focus-group discussion involving 10 participants. We have demonstrated that when an expression is deemed suitable for all situations categorized under both the primary perspective of madness and a related perspective involving exaggerated descriptions of entities, a concept (P) emerges that bears similarity or relevance to the polysemic complex ( bidʒannin\mad ) to which the expression belongs. In such cases, we can consider the related perspective (P') as a member of the polysemic complex ( bidʒannin\mad ). Thus, this study explains how the same metaphor can lead to a complex of multiple meanings in two different languages that are not necessarily related to each other.

Semantic Flowers for Good-for-Games and Deterministic Automata

We present an innovative approach for capturing the complexity of ω-regular languages using the concept of flowers. This semantic tool combines two syntax-based definitions, namely the Mostowski hierarchy of word languages and syntactic flowers. The former is based on deterministic parity automata with a limited number of priorities, while the latter simplifies deterministic parity automata by reducing the number of priorities used, without altering their structure. Synthesising these two approaches yields a semantic concept of flowers, which offers a more effective way of dealing with the complexity of ω-regular languages. This letter provides a comprehensive definition of semantic flowers and shows that it captures the complexity of ω-regular languages. We also show that this natural concept yields simple proofs of the expressive power of good-for-games automata.

Structure shapes the representation of a novel category.

Concepts contain rich structures that support flexible semantic cognition. These structures can be characterized by patterns of feature covariation: Certain features tend to cluster in the same items (e.g., feathers, wings, can fly). Existing computational models demonstrate how this kind of structure can be leveraged to slowly learn the distinctions between categories, on developmental timescales. However, it is not clear whether and how we leverage feature structure to quickly learn a novel category. We thus investigated how the internal structure of a new category is first extracted from experience, with the prediction that feature-based structure would have a rapid and broad influence on the learned category representation. Across three experiments, novel categories were designed with patterns of feature associations determined by carefully constructed graph structures, with Modular graphs-exhibiting strong clusters of feature covariation-compared against Random and Lattice graphs. In Experiment 1, a feature inference task using verbal stimuli revealed that Modular structure broadly facilitated category learning. Experiment 2 replicated this effect in visual categories. In Experiment 3, a statistical learning paradigm revealed that this Modular benefit relates to high-level structure rather than pairwise feature associations and persists even when category structure is incidental to the task. A neural network model was readily able to account for these effects, suggesting that correlational feature structure may be encoded within rapidly learned, distributed category representations. These findings constrain theories of category representation and link theories of category learning with structure learning more broadly. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Representational similarity learning reveals a graded multidimensional semantic space in the human anterior temporal cortex

Abstract Neurocognitive models of semantic memory have proposed that the ventral anterior temporal lobes (vATLs) encode a graded and multidimensional semantic space—yet neuroimaging studies seeking brain regions that encode semantic structure rarely identify these areas. In simulations, we show that this discrepancy may arise from a crucial mismatch between theory and analysis approach. Utilizing an analysis recently formulated to investigate graded multidimensional representations, representational similarity learning (RSL), we decoded semantic structure from ECoG data collected from the vATL cortical surface while participants named line drawings of common items. The results reveal a graded, multidimensional semantic space encoded in neural activity across the vATL, which evolves over time and simultaneously expresses both broad and finer-grained semantic structure among animate and inanimate concepts. The work resolves the apparent discrepancy within the semantic cognition literature and, more importantly, suggests a new approach to discovering representational structure in neural data more generally.

Implementing Cognitive Semantics of Autoepistemic Membership Statements: The Case of Categories with Prototypes

This article presents a model of an architecture of an artificial cognitive agent that performs the function of generating autoepistemic membership statements used to communicate beliefs about the belonging of an observed external object to a category with a prototype. The meaning of statements is described within the model by means of cognitive semantics. The presented proposal builds upon a pre-existing architecture and a semantic model designed for a simpler case of categories without a prototype. The main conclusion is that it is possible to develop an interactive cognitive agent capable of learning about categories with prototypes and producing autoepistemic membership statements fulfilling requirements of Rosch’s standard version of prototype semantics and satisfying pragmatic and logical rules for generating equivalents of these statements in natural languages. Detailed results include the following: an original proposal for an agent’s architecture, a model of an agent’s strategy of learning categories with a prototype, a scheme for determining the computational complexity of particular implementations of the learning strategy, definitions of cognitive semantics for particular cases of autoepistemic membership statements, and an analytical verification of properties of the proposed cognitive semantics. Finally, this article discusses the directions of further development and potential variants of the proposed architecture.