Enhancing Deep Learning Semantics:The Diffusion Sampling and Label-Driven Co-Attention Approach

The advent of self-attention mechanisms within Transformer models has significantly propelled the advancement of deep learning algorithms,yielding outstanding achievements across diverse domains.Nonetheless,self-attention mechanisms falter when applied to datasets with intricate semantic content and extensive dependency structures.In response,this paper introduces a Diffusion Sampling and Label-Driven Co-attention Neural Network(DSLD),which adopts a diffusion sampling method to capture more comprehensive semantic information of the data.Additionally,themodel leverages the joint correlation information of labels and data to introduce the computation of text representation,correcting semantic representationbiases in thedata,andincreasing the accuracyof semantic representation.Ultimately,the model computes the corresponding classification results by synthesizing these rich data semantic representations.Experiments on seven benchmark datasets show that our proposed model achieves competitive results compared to state-of-the-art methods.

Improving Chinese Word Representation with Conceptual Semantics

The meaning of a word includes a conceptual meaning and a distributive meaning.Word embedding based on distribution suffers from insufficient conceptual semantic representation caused by data sparsity,especially for low-frequency words.In knowledge bases,manually annotated semantic knowledge is stable and the essential attributes of words are accurately denoted.In this paper,we propose a Conceptual Semantics Enhanced Word Representation(CEWR)model,computing the synset embedding and hypernym embedding of Chinese words based on the Tongyici Cilin thesaurus,and aggregating it with distributed word representation to have both distributed information and the conceptual meaning encoded in the representation of words.We evaluate the CEWR model on two tasks:word similarity computation and short text classification.The Spearman correlation between model results and human judgement are improved to 64.71%,81.84%,and 85.16%on Wordsim297,MC30,and RG65,respectively.Moreover,CEWR improves the F1 score by 3%in the short text classification task.The experimental results show that CEWR can represent words in a more informative approach than distributed word embedding.This proves that conceptual semantics,especially hypernymous information,is a good complement to distributed word representation.

Ontology Based Ocean Knowledge Representation for Semantic Information Retrieval

The drastic growth of coastal observation sensors results in copious data that provide weather information.The intricacies in sensor-generated big data are heterogeneity and interpretation,driving high-end Information Retrieval(IR)systems.The Semantic Web(SW)can solve this issue by integrating data into a single platform for information exchange and knowledge retrieval.This paper focuses on exploiting the SWbase systemto provide interoperability through ontologies by combining the data concepts with ontology classes.This paper presents a 4-phase weather data model:data processing,ontology creation,SW processing,and query engine.The developed Oceanographic Weather Ontology helps to enhance data analysis,discovery,IR,and decision making.In addition to that,it also evaluates the developed ontology with other state-of-the-art ontologies.The proposed ontology’s quality has improved by 39.28%in terms of completeness,and structural complexity has decreased by 45.29%,11%and 37.7%in Precision and Accuracy.Indian Meteorological Satellite INSAT-3D’s ocean data is a typical example of testing the proposed model.The experimental result shows the effectiveness of the proposed data model and its advantages in machine understanding and IR.

A New Method of Semantic Network Knowledge Representation Based on Extended Petri Net

Abstract： It was discussed that the way to reflect the internal relations between judgment and identification, the two most fundamental ways of thinking or cognition operations, during the course of the semantic network knowledge representation processing. A new extended Petri net is defined based on qualitative mapping, which strengths the expressive ability of the feature of thinking and the mode of action of brain. A model of semantic network knowledge representation based on new Petri net is given. Semantic network knowledge has a more efficient representation and reasoning mechanism. This model not only can reflect the characteristics of associative memory in semantic network knowledge representation, but also can use Petri net to express the criterion changes and its change law of recognition judgment, especially the cognitive operation of thinking based on extraction and integration of sensory characteristics to well express the thinking transition course from quantitative change to qualitative change of human cognition.

Word Net-based lexical semantic classification for text corpus analysis

Many text classifications depend on statistical term measures to implement document representation. Such document representations ignore the lexical semantic contents of terms and the distilled mutual information, leading to text classification errors.This work proposed a document representation method, Word Net-based lexical semantic VSM, to solve the problem. Using Word Net,this method constructed a data structure of semantic-element information to characterize lexical semantic contents, and adjusted EM modeling to disambiguate word stems. Then, in the lexical-semantic space of corpus, lexical-semantic eigenvector of document representation was built by calculating the weight of each synset, and applied to a widely-recognized algorithm NWKNN. On text corpus Reuter-21578 and its adjusted version of lexical replacement, the experimental results show that the lexical-semantic eigenvector performs F1 measure and scales of dimension better than term-statistic eigenvector based on TF-IDF. Formation of document representation eigenvectors ensures the method a wide prospect of classification applications in text corpus analysis.

Semantic Similarity between Ontologies at Different Scales

In the past decade, existing and new knowledge and datasets have been encoded in different ontologies for semantic web and biomedical research. The size of ontologies is often very large in terms of number of concepts and relationships, which makes the analysis of ontologies and the represented knowledge graph computational and time consuming. As the ontologies of various semantic web and biomedical applications usually show explicit hierarchical structures, it is interesting to explore the trade-offs between ontological scales and preservation/precision of results when we analyze ontologies. This paper presents the first effort of examining the capability of this idea via studying the relationship between scaling biomedical ontologies at different levels and the semantic similarity values. We evaluate the semantic similarity between three gene ontology slims (plant, yeast, and candida, among which the latter two belong to the same kingdom-fungi) using four popular measures commonly applied to biomedical ontologies (Resnik, Lin, Jiang-Conrath, and SimRel). The results of this study demonstrate that with proper selection of scaling levels and similarity measures, we can significantly reduce the size of ontologies without losing substantial detail. In particular, the performances of Jiang-Conrath and Lin are more reliable and stable than that of the other two in this experiment, as proven by 1) consistently showing that yeast and candida are more similar (as compared to plant) at different scales, and 2) small deviations of the similarity values after excluding a majority of nodes from several lower scales. This study provides a deeper understanding of the application of semantic similarity to biomedical ontologies, and shed light on how to choose appropriate semantic similarity measures for biomedical engineering. © 2014 Chinese Association of Automation.

Knowledge-Enhanced Bilingual Textual Representations for Cross-Lingual Semantic Textual Similarity

Joint learning of words and entities is advantageous to various NLP tasks, while most of the works focus on single language setting. Cross-lingual representations learning receives high attention recently, but is still restricted by the availability of parallel data. In this paper, a method is proposed to jointly embed texts and entities on comparable data. In addition to evaluate on public semantic textual similarity datasets, a task (cross-lingual text extraction) was proposed to assess the similarities between texts and contribute to this dataset. It shows that the proposed method outperforms cross-lingual representations methods using parallel data on cross-lingual tasks, and achieves competitive results on mono-lingual tasks.

Learning Dual-Layer User Representation for Enhanced Item Recommendation

User representation learning is crucial for capturing different user preferences,but it is also critical challenging because user intentions are latent and dispersed in complex and different patterns of user-generated data,and thus cannot be measured directly.Text-based data models can learn user representations by mining latent semantics,which is beneficial to enhancing the semantic function of user representations.However,these technologies only extract common features in historical records and cannot represent changes in user intentions.However,sequential feature can express the user’s interests and intentions that change time by time.But the sequential recommendation results based on the user representation of the item lack the interpretability of preference factors.To address these issues,we propose in this paper a novel model with Dual-Layer User Representation,named DLUR,where the user’s intention is learned based on two different layer representations.Specifically,the latent semantic layer adds an interactive layer based on Transformer to extract keywords and key sentences in the text and serve as a basis for interpretation.The sequence layer uses the Transformer model to encode the user’s preference intention to clarify changes in the user’s intention.Therefore,this dual-layer user mode is more comprehensive than a single text mode or sequence mode and can effectually improve the performance of recommendations.Our extensive experiments on five benchmark datasets demonstrate DLUR’s performance over state-of-the-art recommendation models.In addition,DLUR’s ability to explain recommendation results is also demonstrated through some specific cases.

Empirical Verification of Swanson’s Caring Processes Found in Nursing Actions: Systematic Review

Caring has long been recognized as central to nursing and is increasingly posited as a core concept although developing a theoretical description of caring which is adequate in the 21st. century continues to be a difficult task for nursing scholars. Consequently, verifying existing theoretical structures of caring remains an ongoing challenge. The aim of this article is to provide empirical verification of the caring processes of “knowing,” “being with,” “doing for,” “enabling” and “maintaining belief” from Swanson’s Middle Range Caring Theory based on the categorization of nursing actions from a systematic literature review on care. Methods: A systematic literature review was conducted in the fields of nursing sciences, medicine and psychology. Purposeful sampling was carried out covering a period from 2003-2013. The final sample included 25 articles. Results: Major themes of nursing actions included “knowing” which consisted of centering, nurturing, informed understanding, assessment skills, communication and respect for individual differences. “Being with” was characterized by intimate relationship, connecting, presencing, emotional adaptability awareness of self/other and decentering. “Doing for” included competence, knowledge, professional/technical skills, helping actions, anticipatory, multidisciplinary and preserving dignity. “Enabling” was characterized by self care, commitment, complexity of care, appropriate communication, information/education, sharing power, enabling choice and ongoing validation. Finally, “maintaining belief” was characterized by spiritual being, humanistic view, harmonious balance, hope, love, and compassion, meaning, and religious and spiritual orientation. Conclusion: Empirical verification was shown for the caring processes described in Swanson’s Caring Theory grounded in concrete nursing actions.

Capturing semantic features to improve Chinese event detection

Current Chinese event detection methods commonly use word embedding to capture semantic representation,but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence.Based on the simple evaluation,it is known that a dependency parser can effectively capture dependency relationships and improve the accuracy of event categorisation.This study proposes a novel architecture that models a hybrid representation to summarise semantic and structural information from both characters and words.This model can capture rich semantic features for the event detection task by incorporating the semantic representation generated from the dependency parser.The authors evaluate different models on kbp 2017 corpus.The experimental results show that the proposed method can significantly improve performance in Chinese event detection.

Word Embeddings and Semantic Spaces in Natural Language Processing

One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.

Building of cognizing semantic map in large-scale semi-unknown environment

The quick response code based artificial labels are applied to provide semantic concepts and relations of surroundings that permit the understanding of complexity and limitations of semantic recognition and scene only with robot's vision.By imitating spatial cognizing mechanism of human,the robot constantly received the information of artificial labels at cognitive-guide points in a wide range of structured environment to achieve the perception of the environment and robot navigation.The immune network algorithm was used to form the environmental awareness mechanism with "distributed representation".The color recognition and SIFT feature matching algorithm were fused to achieve the memory and cognition of scenario tag.Then the cognition-guide-action based cognizing semantic map was built.Along with the continuously abundant map,the robot did no longer need to rely on the artificial label,and it could plan path and navigate freely.Experimental results show that the artificial label designed in this work can improve the cognitive ability of the robot,navigate the robot in the case of semi-unknown environment,and build the cognizing semantic map favorably.

Ontology-Based Crime News Semantic Retrieval System

Every day,the media reports tons of crimes that are considered by a large number of users and accumulate on a regular basis.Crime news exists on the Internet in unstructured formats such as books,websites,documents,and journals.From such homogeneous data,it is very challenging to extract relevant information which is a time-consuming and critical task for the public and law enforcement agencies.Keyword-based Information Retrieval(IR)systems rely on statistics to retrieve results,making it difficult to obtain relevant results.They are unable to understandthe user’s query and thus facewordmismatchesdue to context changes andthe inevitable semanticsof a given word.Therefore,such datasets need to be organized in a structured configuration,with the goal of efficiently manipulating the data while respecting the semantics of the data.An ontological semantic IR systemis needed that can find the right investigative information and find important clues to solve criminal cases.The semantic system retrieves information in view of the similarity of the semantics among indexed data and user queries.In this paper,we develop anontology-based semantic IRsystemthat leverages the latest semantic technologies including resource description framework(RDF),semantic protocol and RDF query language(SPARQL),semantic web rule language(SWRL),and web ontology language(OWL).We have conducted two experiments.In the first experiment,we implemented a keyword-based textual IR systemusing Apache Lucene.In the second experiment,we implemented a semantic systemthat uses ontology to store the data and retrieve precise results with high accuracy using SPARQL queries.The keyword-based system has filtered results with 51%accuracy,while the semantic system has filtered results with 95%accuracy,leading to significant improvements in the field and opening up new horizons for researchers.

“SEMANTIC” in a Digital Curation Model

Purpose:This study attempts to propose an abstract model by gathering concepts that can focus on resource representation and description in a digital curation model and suggest a conceptual model that emphasizes semantic enrichment in a digital curation model.Design/methodology/approach:This study conducts a literature review to analyze the preceding curation models,DCC CLM,DCC&U,UC3,and DCN.Findings:The concept of semantic enrichment is expressed in a single word,SEMANTIC in this study.The Semantic Enrichment Model,SEMANTIC has elements,subject,extraction,multi-language,authority,network,thing,identity,and connect.Research limitations:This study does not reflect the actual information environment because it focuses on the concepts of the representation of digital objects.Practical implications:This study presents the main considerations for creating and reinforcing the description and representation of digital objects when building and developing digital curation models in specific institutions.Originality/value:This study summarizes the elements that should be emphasized in the representation of digital objects in terms of information organization.

SEMANTIC CONSTRAINT MODELER FOR 2D AND 3D GEOMETRY

Design changes for 2D & 3D geometry are the most important features in the process of product design.Constraint modeling for variationl geometry based on geometric reasoning is one of the best approaches for this goal.However,it is difficult for the proposed systems to maintain or handle the consistency and completeness of the constraint model of the design objects.To change this situation,a semantic model and its control approach are presented,aiming at the integration of the data,knowledge and method related to design objects.Aconstraint definition system for in- teractively defining the semantic model and a prototype modeler based on the semantic model are also implemented to examine the idea which is extended to 3D geometric design too.

基于生成式逻辑的古籍文献自动化置标语义框架构建与应用研究

目前,我国古籍文献的数字化以文献扫描、粗粒度文件管理等浅层知识服务为主,生成式人工智能技术的发展为古籍文献数字化的深度化提供了新的机遇。文章基于框架语义学理论构建置标语义逻辑结构框架,以生成式逻辑向大语言模型提出问题,递归提取古籍语料中深层语义内容,并将其输出为符合置标语义框架的结构化数据,使古籍文本在基础语义层面获得统一的处理逻辑。古籍自动置标语义框架能够实现大规模自动化古籍文献内容结构生成式表征,为古籍整理智能化转型提供一种自动可行的技术方案。

基于口述历史资源的名人历史事件语义模型构建及实证研究

[目的/意义]口述历史资源具有重要的史料价值和精神价值,具有跨图书馆、档案馆、博物馆、科技馆等多领域的异构资源特征,由口述历史资源析出的名人历史事件,其“自下而上”研究历史的新途径,受到了历史、档案、图情领域的普遍重视。事件的知识组织与应用一直是知识处理的重点和难点问题,而在数字人文视角下,名人历史事件的知识化是对名人特藏资源进行知识重组、价值挖掘和叙事展演的重要基础。[方法/过程]在前人研究的基础上,本文对名人历史事件的内涵、特征和应用需求进行了总结与分析,构建了名人历史事件语义模型,并以科学家李政道和其创办CUSPEA事件为例进行语义模型的实例化构建。[结果/结论]在名人历史事件语义模型基础上所建设的图数据库,能够形成更具灵活性、细粒度、可扩展、相关联的实体关系和知识,实现不同类型的用户对名人特色资源进行语义级查询、主题性聚合、叙事化展示和可视化呈现的知识表示。

面向视频数据的多模态情感分析

多模态情感分析旨在从文本、图像和音频数据中提取和整合语义信息,从而识别在线视频中说话者的情感状态。尽管多模态融合方案在此研究领域已取得一定成果,但是已有方法在处理模态间分布差异和关系知识的融合方面仍有欠缺,为此,提出一种多模态情感分析方法。设计一种多模态提示门(MPG)模块,其能够将非语言信息转换为融合文本上下文的提示,利用文本信息对非语言信号的噪声进行过滤,得到包含丰富语义信息的提示,以增强模态间的信息整合。此外,提出一种实例到标签的对比学习框架,在语义层面上区分隐空间中的不同标签以进一步优化模型输出。在3个大规模情感分析数据集上的实验结果表明,该方法的二分类精度相对次优模型提高了约0.7%,三分类精度提高了超过2.5%,达到0.671。该方法能够为将多模态情感分析引入用户画像、视频理解、AI面试等领域提供参考。

语言符号与知觉符号表征对外语词汇习得的影响比较:来自行为与脑电的实验证据

通过行为与脑电实验技术,比较外语词汇学习过程中,语言符号与知觉符号表征对词汇记忆编码与再认的影响过程,从而考察语义表征对词汇习得的影响机制。行为结果表明,语言符号与知觉符号表征条件下被试对词汇学习效果的主观判断无显著差异,但后者比前者有更高的词汇再认正确率。脑电结果表明,对于词汇编码阶段,相较语言符号表征,知觉符号表征在编码晚期诱发更正的LPC成分;对于词汇再认阶段,知觉符号表征条件诱发更大N400成分,且脑电时频分析表明该条件下出现更为明显的μ波抑制及θ波功率增强现象。研究结果综合表明,与语言符号表征便捷但非模态化的语义加工相比,知觉符号表征加深了词汇晚期编码的深度,并通过知觉模拟,利用多模态信息提高了词汇的形象化再认,从而推动了再认阶段的语义检索,最终内隐性地提高了词汇学习效果。