Large-scale Semantic Network Research Articles

Connector hubs in semantic network contribute to creative thinking.

Semantic memory offers a rich repository of raw materials (e.g., various concepts and connections between concepts) for creative thinking, represented as a semantic network. Similar to other networks, the semantic network exhibits a modular structure characterized by modules with dense internal connections and sparse connections between them. This organizational principle facilitates the routine storage and retrieval of information but may impede creativity. The present study investigated the effect of hub concepts with varying connection patterns on creative thinking from the perspective of a modular structured semantic network. By analyzing a large-scale semantic network, connector hubs (C-hubs) and provincial hubs (P-hubs) were identified based on their intra- and intermodule connections. These hubs were used as cue words in the alternative uses task, a widely used measure of creative thinking. Across four experiments, behavioral and neural evidence indicated that C-hubs facilitate the generation of more novel and remote ideas compared to P-hubs. However, this effect is predominantly observed in the early stage of the creative thinking process, involving changes in brain activation and functional connectivity in core regions of the default mode network and the frontoparietal network, including the dorsolateral prefrontal cortex, angular gyrus, and precuneus. Neural findings suggest that the superior performance of C-hubs relies on stronger interactions between automatic spreading activation, controlled semantic retrieval, and attentional regulation of salient information. These results provide insight into how concepts with varying semantic connection patterns facilitate and constrain different stages of the creative thinking process through the modular structure of semantic network. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Overview of knowledge reasoning for knowledge graph

Knowledge graphs are large-scale semantic networks that considerably impact knowledge representation. Mining hidden knowledge from existing data, including triplet knowledge reasoning, is a primary objective of knowledge graphs. With the development of Neural Network (NN) and Deep Learning (DL), the interpretability of triplet knowledge reasoning gradually decreases; furthermore, what machines learn is not actual reasoning but digital reasoning shortcuts. To solve this problem, more background knowledge needs to be introduced into knowledge graphs: causal graphs can offer valuable causal logic knowledge for reasoning; temporal quadruples can provide essential temporal distribution details; and commonsense graphs can furnish pertinent commonsense understanding to support reasoning. In recent years, many scholars have incorporated additional background knowledge into knowledge graphs to construct more complex reasoning mechanisms. This paper reviews the basic concepts and definitions of knowledge reasoning and the reasoning methods used for knowledge graphs. Specifically, we dissect the reasoning methods into four categories: triplet reasoning, causal inference, temporal inference, and commonsense reasoning. Finally, we discuss the remaining challenges and research opportunities related to knowledge graph reasoning.

Knowledge graph completion using topological correlation and multi-perspective independence

Knowledge graphs (KGs) are large-scale semantic networks designed to describe real-world facts. Existing KGs contain only a fraction of what is really happening in the real life. Knowledge graph completion (KGC) has attracted attention because it can automatically infer and predict missing links in the KGs. The classical geometric, tensor decomposition and convolutional neural network (CNN) based models generate expressive feature embeddings, but these models treat triples independently and thus fail to cover the hidden information that is inherently implicit in the local neighborhood surrounding a triple. Recent works have introduced Graph Convolutional Network (GCN) into KGC task for leveraging the rich structural information in complex graphs. However, existing GCN-based models have limitations in relational topology distinction and multi-perspective feature aggregation. As multi-relational graphs, KGs display intrinsic heterogeneous structures and rich entity types. Therefore, ignoring the rich structural information and perspective features will greatly limit the expressive power of these models. In this paper, we propose multi-relational GCNs for modeling topological correlation and multi-perspective independence (CorIn). Specifically, we propose a multi-integration ring relational topology to fine-grained select neighbors according to relational correlation patterns, and capture the independence of multi-perspective feature groups by mutual information minimization. Our model adaptively utilizes an embedding learning design that can leverage a variety of entity-relation composition operations from classical KGC models. We evaluate our model on the public benchmark datasets and achieve marked performance gains in comparison to state-of-the-art methods.

Exploring relationship between emotion and probiotics with knowledge graphs.

Researchers have identified gut microbiota that interact with brain regions associated with emotion and mood. Literature reviews of those associations rely on rigorous systematic approaches and labor-intensive investments. Here we explore how knowledge graph, a large scale semantic network consisting of entities and concepts as well as the semantic relationships among them, is incorporated into the emotion-probiotic relationship exploration work. We propose an end-to-end emotion-probiotics relationship exploration method with an integrated medical knowledge graph, which incorporates the text mining output of knowledge graph, concept reasoning and evidence classification. Specifically, a knowledge graph for probiotics is built based on a text-mining analysis of PubMed, and further used to retrieve triples of relationships with reasoning logistics. Then specific relationships are annotated and evidence levels are retrieved to form a new evidence-based emotion-probiotic knowledge graph. Based on the probiotics knowledge graph with 40,442,404 triples, totally 1453 PubMed articles were annotated in both the title level and abstract level, and the evidence levels were incorporated to the visualization of the explored emotion-probiotic relationships. Finally, we got 4131 evidenced emotion-probiotic associations. The evidence-based emotion-probiotic knowledge graph construction work demonstrates an effective reasoning based pipeline of relationship exploration. The annotated relationship associations are supposed be used to help researchers generate scientific hypotheses or create their own semantic graphs for their research interests.

“BATTLES OVER ISSUES” IN NETWORKED PUBLICS: INVESTIGATING THE DISCURSIVE MOBILIZATION OF THE ANTIFASCIST FRAME ON TWITTER

In this article we explore the discursive mobilization of movement frames within networked publics—a form of unorganized digital activism through which movement organizations, activists, and citizens politicize ordinary conversations by engaging in adversarial meaning-making dynamics online. Leaning on large-scale semantic network analysis and content analysis, we investigate the mobilization of the frame of antifascism within the conversation that sparked on Twitter after the brutal shooting of a group of African citizens by an Italian neo-fascist militant in 2018. We pay particular attention to how the discursive mobilization of the frame of antifascism occurs immediately after the shooting and how it evolves particularly in connection with offline protests. Our results shed light on the fluid nature of discursive mobilization patterns which underpin both the identification with the antifascist tradition and attempts to delegitimize this instance of collective action.

Semantic Networks for Engineering Design: State of the Art and Future Directions

Abstract In the past two decades, there has been increasing use of semantic networks in engineering design for supporting various activities, such as knowledge extraction, prior art search, idea generation and evaluation. Leveraging large-scale pre-trained graph knowledge databases to support engineering design-related natural language processing (NLP) tasks has attracted a growing interest in the engineering design research community. Therefore, this paper aims to provide a survey of the state-of-the-art semantic networks for engineering design and propositions of future research to build and utilize large-scale semantic networks as knowledge bases to support engineering design research and practice. The survey shows that WordNet, ConceptNet and other semantic networks, which contain common-sense knowledge or are trained on non-engineering data sources, are primarily used by engineering design researchers to develop methods and tools. Meanwhile, there are emerging efforts in constructing engineering and technical-contextualized semantic network databases, such as B-Link and TechNet, through retrieving data from technical data sources and employing unsupervised machine learning approaches. On this basis, we recommend six strategic future research directions to advance the development and uses of large-scale semantic networks for artificial intelligence applications in engineering design.

Distant connectivity and multiple-step priming in large-scale semantic networks.

We examined 3 different network models of representing semantic knowledge (5,018-word directed and undirected step distance networks, and an association-correlation network) to predict lexical priming effects. In Experiment 1, participants made semantic relatedness judgments for word pairs with varying path lengths. Response latencies for judgments followed a quadratic relationship with network path lengths, replicating and extending a recent pattern reported by Kenett, Levi, Anaki, and Faust (2017) for an 800-word association-correlation network in Hebrew. In Experiment 2, participants identified target words in a progressive demasking task, immediately following a briefly presented prime (120 ms). Response latencies to identify the target showed a linear trend for all network path lengths. Importantly, there were statistically significant differences between relatively distant words in the step distance networks, for example, path lengths 4 and beyond, suggesting that association networks can indeed capture distant functional semantic relationships. Additional comparisons with 2 distributional models (LSA and word2vec) suggested that distributional models also successfully predicted response latencies, although there appear to be fundamental differences in the types of semantic relationships captured by the different models. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

A Context-Based Disambiguation Model for Sentiment Concepts Using a Bag-of-Concepts Approach

With the widespread dissemination of user-generated content on different social networks, and online consumer systems such as Amazon, the quantity of opinionated information available on the Internet has been increased. One of the main tasks of the sentiment analysis is to detect polarity within a text. The existing polarity detection methods mainly focus on keywords and their naive frequency counts; however, they less regard the meanings and implicit dimensions of the natural concepts. Although background knowledge plays a critical role in determining the polarity of concepts, it has been disregarded in polarity detection methods. This study presents a context-based model to solve ambiguous polarity concepts using commonsense knowledge. First, a model is presented to generate a source of ambiguous sentiment concepts based on SenticNet by computing the probability distribution. Then the model uses a bag-of-concepts approach to remove ambiguities and semantic augmentation with the ConceptNet handling to overcome lost knowledge. ConceptNet is a large-scale semantic network with a large number of commonsense concepts. In this paper, the point mutual information (PMI) measure is used to select the contextual concepts having strong relationships with ambiguous concepts. The polarity of the ambiguous concepts is precisely detected using positive/negative contextual concepts and the relationship of the concepts in the semantic knowledge base. The text representation scheme is semantically enriched using Numberbatch, which is a word embedding model based on the concepts from the ConceptNet semantic network. The proposed model is evaluated by applying a corpus of product reviews, called Semeval. The experimental results revealed an accuracy rate of 82.07%, representing the effectiveness of the proposed model.

Knowledge Embedding with Geospatial Distance Restriction for Geographic Knowledge Graph Completion

A Geographic Knowledge Graph (GeoKG) links geographic relation triplets into a large-scale semantic network utilizing the semantic of geo-entities and geo-relations. Unfortunately, the sparsity of geo-related information distribution on the web leads to a situation where information extraction systems can hardly detect enough references of geographic information in the massive web resource to be able to build relatively complete GeoKGs. This incompleteness, due to missing geo-entities or geo-relations in GeoKG fact triplets, seriously impacts the performance of GeoKG applications. In this paper, a method with geospatial distance restriction is presented to optimize knowledge embedding for GeoKG completion. This method aims to encode both the semantic information and geospatial distance restriction of geo-entities and geo-relations into a continuous, low-dimensional vector space. Then, the missing facts of the GeoKG can be supplemented through vector operations. Specifically, the geospatial distance restriction is realized as the weights of the objective functions of current translation knowledge embedding models. These optimized models output the optimized representations of geo-entities and geo-relations for the GeoKG’s completion. The effects of the presented method are validated with a real GeoKG. Compared with the results of the original models, the presented method improves the metric Hits@10(Filter) by an average of 6.41% for geo-entity prediction, and the Hits@1(Filter) by an average of 31.92%, for geo-relation prediction. Furthermore, the capacity of the proposed method to predict the locations of unknown entities is validated. The results show the geospatial distance restriction reduced the average error distance of prediction by between 54.43% and 57.24%. All the results support the geospatial distance restriction hiding in the GeoKG contributing to refining the embedding representations of geo-entities and geo-relations, which plays a crucial role in improving the quality of GeoKG completion.

Learning From Short Text Streams With Topic Drifts

Short text streams such as search snippets and micro blogs have been popular on the Web with the emergence of social media. Unlike traditional normal text streams, these data present the characteristics of short length, weak signal, high volume, high velocity, topic drift, etc. Short text stream classification is hence a very challenging and significant task. However, this challenge has received little attention from the research community. Therefore, a new feature extension approach is proposed for short text stream classification with the help of a large-scale semantic network obtained from a Web corpus. It is built on an incremental ensemble classification model for efficiency. First, more semantic contexts based on the senses of terms in short texts are introduced to make up of the data sparsity using the open semantic network, in which all terms are disambiguated by their semantics to reduce the noise impact. Second, a concept cluster-based topic drifting detection method is proposed to effectively track hidden topic drifts. Finally, extensive studies demonstrate that as compared to several well-known concept drifting detection methods in data stream, our approach can detect topic drifts effectively, and it enables handling short text streams effectively while maintaining the efficiency as compared to several state-of-the-art short text classification approaches.

Leveraging Large-Scale Semantic Networks for Adaptive Robot Task Learning and Execution.

This work seeks to leverage semantic networks containing millions of entries encoding assertions of commonsense knowledge to enable improvements in robot task execution and learning. The specific application we explore in this project is object substitution in the context of task adaptation. Humans easily adapt their plans to compensate for missing items in day-to-day tasks, substituting a wrap for bread when making a sandwich, or stirring pasta with a fork when out of spoons. Robot plan execution, however, is far less robust, with missing objects typically leading to failure if the robot is not aware of alternatives. In this article, we contribute a context-aware algorithm that leverages the linguistic information embedded in the task description to identify candidate substitution objects without reliance on explicit object affordance information. Specifically, we show that the task context provided by the task labels within the action structure of a task plan can be leveraged to disambiguate information within a noisy large-scale semantic network containing hundreds of potential object candidates to identify successful object substitutions with high accuracy. We present two extensive evaluations of our work on both abstract and real-world robot tasks, showing that the substitutions made by our system are valid, accepted by users, and lead to a statistically significant reduction in robot learning time. In addition, we report the outcomes of testing our approach with a large number of crowd workers interacting with a robot in real time.

A Large Probabilistic Semantic Network Based Approach to Compute Term Similarity

Measuring semantic similarity between two terms is essential for a variety of text analytics and understanding applications. Currently, there are two main approaches for this task, namely the knowledge based and the corpus based approaches. However, existing approaches are more suitable for semantic similarity between words rather than the more general multi-word expressions (MWEs), and they do not scale very well. Contrary to these existing techniques, we propose an efficient and effective approach for semantic similarity using a large scale semantic network. This semantic network is automatically acquired from billions of web documents. It consists of millions of concepts, which explicitly model the context of semantic relationships. In this paper, we first show how to map two terms into the concept space, and compare their similarity there. Then, we introduce a clustering approach to orthogonalize the concept space in order to improve the accuracy of the similarity measure. Finally, we conduct extensive studies to demonstrate that our approach can accurately compute the semantic similarity between terms of MWEs and with ambiguity, and significantly outperforms 12 competing methods under Pearson Correlation Coefficient. Meanwhile, our approach is much more efficient than all competing algorithms, and can be used to compute semantic similarity in a large scale.

Going beyond Inferior Prefrontal Involvement in Semantic Control: Evidence for the Additional Contribution of Dorsal Angular Gyrus and Posterior Middle Temporal Cortex

Semantic cognition requires a combination of semantic representations and executive control processes to direct activation in a task- and time-appropriate fashion [Jefferies, E., & Lambon Ralph, M. A. Semantic impairment in stroke aphasia versus semantic dementia: A case-series comparison. Brain, 129, 2132-2147, 2006]. We undertook a formal meta-analysis to investigate which regions within the large-scale semantic network are specifically associated with the executive component of semantic cognition. Previous studies have described in detail the role of left ventral pFC in semantic regulation. We examined 53 studies that contrasted semantic tasks with high > low executive requirements to determine whether cortical regions beyond the left pFC show the same response profile to executive semantic demands. Our findings revealed that right pFC, posterior middle temporal gyrus (pMTG) and dorsal angular gyrus (bordering intraparietal sulcus) were also consistently recruited by executively demanding semantic tasks, demonstrating patterns of activation that were highly similar to the left ventral pFC. These regions overlap with the lesions in aphasic patients who exhibit multimodal semantic impairment because of impaired regulatory control (semantic aphasia)-providing important convergence between functional neuroimaging and neuropsychological studies of semantic cognition. Activation in dorsal angular gyrus and left ventral pFC was consistent across all types of executive semantic manipulation, regardless of whether the task was receptive or expressive, whereas pMTG activation was only observed for manipulation of control demands within receptive tasks. Second, we contrasted executively demanding tasks tapping semantics and phonology. Our findings revealed substantial overlap between the two sets of contrasts within left ventral pFC, suggesting this region underpins domain-general control mechanisms. In contrast, we observed relative specialization for semantic control within pMTG as well as the most ventral aspects of left pFC (BA 47), consistent with our proposal of a distributed network underpinning semantic control.

BUILDING SEMANTIC NETWORKS FROM PLAIN TEXT AND WIKIPEDIA WITH APPLICATION TO SEMANTIC RELATEDNESS AND NOUN COMPOUND PARAPHRASING

The construction of suitable and scalable representations of semantic knowledge is a core challenge in Semantic Computing. Manually created resources such as WordNet have been shown to be useful for many AI and NLP tasks, but they are inherently restricted in their coverage and scalability. In addition, they have been challenged by simple distributional models on very large corpora, questioning the advantage of structured knowledge representations. We present a framework for building large-scale semantic networks automatically from plain text and Wikipedia articles using only linguistic analysis tools. Our constructed resources cover up to 2 million concepts and were built in less than 6 days. Using the task of measuring semantic relatedness, we show that we achieve results comparable to the best WordNet based methods as well as the best distributional methods while using a corpus of a size several magnitudes smaller. In addition, we show that we can outperform both types of methods by combining the results of our two network variants. Initial experiments on noun compound paraphrasing show similar results, underlining the quality as well as the flexibility of our constructed resources.

Executive Semantic Processing Is Underpinned by a Large-scale Neural Network: Revealing the Contribution of Left Prefrontal, Posterior Temporal, and Parietal Cortex to Controlled Retrieval and Selection Using TMS

To understand the meanings of words and objects, we need to have knowledge about these items themselves plus executive mechanisms that compute and manipulate semantic information in a task-appropriate way. The neural basis for semantic control remains controversial. Neuroimaging studies have focused on the role of the left inferior frontal gyrus (LIFG), whereas neuropsychological research suggests that damage to a widely distributed network elicits impairments of semantic control. There is also debate about the relationship between semantic and executive control more widely. We used TMS in healthy human volunteers to create "virtual lesions" in structures typically damaged in patients with semantic control deficits: LIFG, left posterior middle temporal gyrus (pMTG), and intraparietal sulcus (IPS). The influence of TMS on tasks varying in semantic and nonsemantic control demands was examined for each region within this hypothesized network to gain insights into (i) their functional specialization (i.e., involvement in semantic representation, controlled retrieval, or selection) and (ii) their domain dependence (i.e., semantic or cognitive control). The results revealed that LIFG and pMTG jointly support both the controlled retrieval and selection of semantic knowledge. IPS specifically participates in semantic selection and responds to manipulations of nonsemantic control demands. These observations are consistent with a large-scale semantic control network, as predicted by lesion data, that draws on semantic-specific (LIFG and pMTG) and domain-independent executive components (IPS).

ASKNET: CREATING AND EVALUATING LARGE SCALE INTEGRATED SEMANTIC NETWORKS

Extracting semantic information from multiple natural language sources and combining that information into a single unified resource is an important and fundamental goal for natural language processing. Large scale resources of this kind can be useful for a wide variety of tasks including question answering, word sense disambiguation and knowledge discovery. A single resource representing the information in multiple documents can provide significantly more semantic information than is available from the documents considered independently. The ASKNet system utilises existing NLP tools and resources, together with spreading activation based techniques, to automatically extract semantic information from a large number of English texts, and combines that information into a large scale semantic network. The initial emphasis of the ASKNet system is on wide-coverage, robustness and speed of construction. In this paper we show how a network consisting of over 1.5 million nodes and 3.5 million edges, more than twice as large as any network currently available, can be created in less than 3 days. Evaluation of large-scale semantic networks is a difficult problem. In order to evaluate ASKNet we have developed a novel evaluation metric based on the notion of a network "core" and employed human evaluators to determine the precision of various components of that core. We have applied this evaluation to networks created from randomly chosen articles used by DUC (Document Understanding Conference). The results are highly promising: almost 80% precision in the semantic core of the networks.

Teaching Machines about Everyday Life

In order to build software that can deeply understand people and our problems, we require computational tools that give machines the capacity to learn and reason about everyday life. We describe three commonsense knowledge bases that take unconventional approaches to representing, acquiring, and reasoning with large quantities of commonsense knowledge. Each adopts a different approach — ConceptNet is a large-scale semantic network, LifeNet is a probabilistic graphical model, and StoryNet is a database of story-scripts. We describe the evolution, architecture and operation of these three systems, and conclude with a discussion of how we might combine them into an integrated commonsense reasoning system.