Bridge Ontology: A Multi-Ontologies-Based Approach for Semantic Annotation

Representing the relationships between ontologies is the key problem of semantic annotations based on multi-ontologies. Traditional approaches only had the ability of denoting the simple concept subsumption relations between ontologies. Through analyzing and classifying the relationships between ontologies, the idea of bridge ontology was proposed, which had the powerful capability of expressing the complex relationships between concepts and relationships between relations in multi-ontologies. Meanwhile, a new approach employing bridge ontology was proposed to deal with the multi-ontologies-based semantic annotation problem. The bridge ontology is a peculiar ontology, which can be created and maintained conveniently, and is effective in the multi-ontologies-based semantic annotation. The approach using bridge ontology has the advantages of low-cost, scalable, robust in the web circumstance, and avoiding the unnecessary ontology extending and integration. Key words semantic web - bridge ontology - multi-ontologies - semantic annotation CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China (60373066, 60303024). National Grand Fundamental Research 973 Program of China (2002CB312000), National Re-search Foundation for the Doctoral Program of Higher Education of China (20020286004)Biography: WANG Peng (1977-), male, Ph.D candidate, research direction: semantic web, ontology, and knowledge representation on the Web.

Ontology-Based Semantic Annotation for Problem Set Archives in the Web

Aimming at the difficulty in getting semantic informarton from each problem in problem set archives, We propose a new method of ontology based semantic annotation for problem set archives, which utilizes programming knowledge domain ontology to add semantic annotations to problems in the Web. The system we developed adds semantic annotation for each problem in the form of Extensible Makeup Language. Our method overcomes the difficulty of extracting semantics from problem set archives and the efficiency of this method is demonstrated through a case study. Having semantic annotations of problems, a student can efficiently locate the problems that logically corre spond to his knowledge.

Semi-supervised learning based probabilistic latent semantic analysis for automatic image annotation

In recent years,multimedia annotation problem has been attracting significant research attention in multimedia and computer vision areas,especially for automatic image annotation,whose purpose is to provide an efficient and effective searching environment for users to query their images more easily. In this paper,a semi-supervised learning based probabilistic latent semantic analysis( PLSA) model for automatic image annotation is presenred. Since it's often hard to obtain or create labeled images in large quantities while unlabeled ones are easier to collect,a transductive support vector machine( TSVM) is exploited to enhance the quality of the training image data. Then,different image features with different magnitudes will result in different performance for automatic image annotation. To this end,a Gaussian normalization method is utilized to normalize different features extracted from effective image regions segmented by the normalized cuts algorithm so as to reserve the intrinsic content of images as complete as possible. Finally,a PLSA model with asymmetric modalities is constructed based on the expectation maximization( EM) algorithm to predict a candidate set of annotations with confidence scores. Extensive experiments on the general-purpose Corel5k dataset demonstrate that the proposed model can significantly improve performance of traditional PLSA for the task of automatic image annotation.

Semantic image annotation based on GMM and random walk model

Automatic image annotation has been an active topic of research in computer vision and pattern recognition for decades.A two stage automatic image annotation method based on Gaussian mixture model(GMM) and random walk model(abbreviated as GMM-RW) is presented.To start with,GMM fitted by the rival penalized expectation maximization(RPEM) algorithm is employed to estimate the posterior probabilities of each annotation keyword.Subsequently,a random walk process over the constructed label similarity graph is implemented to further mine the potential correlations of the candidate annotations so as to capture the refining results,which plays a crucial role in semantic based image retrieval.The contributions exhibited in this work are multifold.First,GMM is exploited to capture the initial semantic annotations,especially the RPEM algorithm is utilized to train the model that can determine the number of components in GMM automatically.Second,a label similarity graph is constructed by a weighted linear combination of label similarity and visual similarity of images associated with the corresponding labels,which is able to avoid the phenomena of polysemy and synonym efficiently during the image annotation process.Third,the random walk is implemented over the constructed label graph to further refine the candidate set of annotations generated by GMM.Conducted experiments on the standard Corel5 k demonstrate that GMM-RW is significantly more effective than several state-of-the-arts regarding their effectiveness and efficiency in the task of automatic image annotation.

Image Semantic Automatic Annotation by Relevance Feedback

A large semantic gap exists between content based index retrieval(CBIR) and high-level semantic,additional semantic information should be attached to the images,it refers in three respects including semantic representation model,semantic information building and semantic retrieval techniques.In this paper,we introduce an associated semantic network and an automatic semantic annotation system.In the system,a semantic network model is employed as the semantic representation model,it uses semantic Key words,linguistic ontology and low-level features in semantic similarity calculating.Through several times of users' relevance feedback,semantic network is enriched automatically.To speed up the growth of semantic network and get a balance annotation,semantic seeds and semantic loners are employed especially.

Heuristics based semantic annotation of biodiversity documents in Chinese

Purpose: To design an efficient high-performance algorithm for semantic annotation of biodiversity documents in Chinese.Design/methodology/approach: Data set consists of 1,000 randomly selected documents from Flora of China. Comparative evaluation of the proposed approach with the Na ve Bayes algorithm have been developed before for the same purpose.Findings: Experimental results show that the heuristics based algorithm outperformed the Na ve Bayes algorithm. The use of leading words helped improving the annotation performance while prioritizing rule application based on their weights had no significant impact on algorithm performance.Research limitations: The ICTCLAS was used to identify word boundaries off-shelf without optimatization for biodiversity domain. This may have not made the best use of the tool.Practical implications & Originality/value: The performance of heuristics based approach,enhanced by leading words analysis, reached an F value of 0.9216, which is sufficiently accurate for practical use.

Ontology-Based News Linking for Semantic Temporal Queries

Daily newspapers publish a tremendous amount of information disseminated through the Internet.Freely available and easily accessible large online repositories are not indexed and are in an un-processable format.The major hindrance in developing and evaluating existing/new monolingual text in an image is that it is not linked and indexed.There is no method to reuse the online news images because of the unavailability of standardized benchmark corpora,especially for South Asian languages.The corpus is a vital resource for developing and evaluating text in an image to reuse local news systems in general and specifically for the Urdu language.Lack of indexing,primarily semantic indexing of the daily news items,makes news items impracticable for any querying.Moreover,the most straightforward search facility does not support these unindexed news resources.Our study addresses this gap by associating and marking the newspaper images with one of the widely spoken but under-resourced languages,i.e.,Urdu.The present work proposed a method to build a benchmark corpus of news in image form by introducing a web crawler.The corpus is then semantically linked and annotated with daily news items.Two techniques are proposed for image annotation,free annotation and fixed cross examination annotation.The second technique got higher accuracy.Build news ontology in protégéusing OntologyWeb Language(OWL)language and indexed the annotations under it.The application is also built and linked with protégéso that the readers and journalists have an interface to query the news items directly.Similarly,news items linked together will provide complete coverage and bring together different opinions at a single location for readers to do the analysis themselves.

Semantic Web与基于语义的网络信息检索

本文描述网络环境语义检索的需求 ,分析SemanticWeb的组成框架 ,探讨概念集 (ontologies)及其定义和标记语言 ,并介绍基于概念集的信息资源语义标注和语义推理基本过程。

Fusing PLSA model and Markov random fields for automatic image annotation

A novel image auto-annotation method is presented based on probabilistic latent semantic analysis(PLSA) model and multiple Markov random fields(MRF).A PLSA model with asymmetric modalities is first constructed to estimate the joint probability between images and semantic concepts,then a subgraph is extracted served as the corresponding structure of Markov random fields and inference over it is performed by the iterative conditional modes so as to capture the final annotation for the image.The novelty of our method mainly lies in two aspects:exploiting PLSA to estimate the joint probability between images and semantic concepts as well as multiple MRF to further explore the semantic context among keywords for accurate image annotation.To demonstrate the effectiveness of this approach,an experiment on the Corel5 k dataset is conducted and its results are compared favorably with the current state-of-the-art approaches.

Exploiting PLSA model and conditional random field for refining image annotation

This paper presents a new method for refining image annotation by integrating probabilistic la- tent semantic analysis （PLSA） with conditional random field （CRF）. First a PLSA model with asymmetric modalities is constructed to predict a candidate set of annotations with confidence scores, and then model semantic relationship among the candidate annotations by leveraging conditional ran- dom field. In CRF, the confidence scores generated lay the PLSA model and the Fliekr distance be- tween pairwise candidate annotations are considered as local evidences and contextual potentials re- spectively. The novelty of our method mainly lies in two aspects ： exploiting PLSA to predict a candi- date set of annotations with confidence scores as well as CRF to further explore the semantic context among candidate annotations for precise image annotation. To demonstrate the effectiveness of the method proposed in this paper, an experiment is conducted on the standard Corel dataset and its re- sults are ＇compared favorably with several state-of-the-art approaches.

Introducing semantic information into motion graph

To improve motion graph based motion synthesis,semantic control was introduced.Hybrid motion features including both numerical and user-defined semantic relational features were extracted to encode the characteristic aspects contained in the character's poses of the given motion sequences.Motion templates were then automatically derived from the training motions for capturing the spatio-temporal characteristics of an entire given class of semantically related motions.The data streams of motion documents were automatically annotated with semantic motion class labels by matching their respective motion class templates.Finally,the semantic control was introduced into motion graph based human motion synthesis.Experiments of motion synthesis demonstrate the effectiveness of the approach which enables users higher level of semantically intuitive control and high quality in human motion synthesis from motion capture database.

Combining Generative/Discriminative Learning for Automatic Image Annotation and Retrieval

In order to bridge the semantic gap exists in image retrieval, this paper propose an approach combining generative and discriminative learning to accomplish the task of automatic image annotation and retrieval. We firstly present continuous probabilistic latent semantic analysis (PLSA) to model continuous quantity. Furthermore, we propose a hybrid framework which employs continuous PLSA to model visual features of images in generative learning stage and uses ensembles of classifier chains to classify the multi-label data in discriminative learning stage. Since the framework combines the advantages of generative and discriminative learning, it can predict semantic annotation precisely for unseen images. Finally, we conduct a series of experiments on a standard Corel dataset. The experiment results show that our approach outperforms many state-of-the-art approaches.

An integrated document retrieval method combining entity annotation and keyword index:A KIM platform implementation

Purpose: The objective of this paper is to testify the effect of ontology-based semantic annotation on the performance of document retrieval.Design/methodology/approach: An integrated document retrieval method is put forward in this paper, in which the entities of documents are annotated by the upper ontology and domain ontology, then the documents are further indexed by the entity annotation as well as traditional keywords.Findings: The research result shows that the structured entity retrieval and relation retrieval can be realized by the ontology-based entity index, which is beyond the ability of the tradition keyword-based retrieval. Meanwhile, the experiment shows that the recall and precision of document retrieval are improved effectively.Research limitations: Due to the small amount of our current tourism domain ontology, the document retrieval with the ontology-based semantic index is limited by the size of ontology and the precision of semantic annotation. Meanwhile, the semantic annotation algorithm mainly relies on the current information extraction strategy of KIM Platform. Therefore,the performance of disambiguation and relation extraction algorithm need to be further improved.Practical implications: Our method can improve the efficiency of document retrieval system,which facilitates the knowledge and document management in corporations, governments and other organizations.Originality/value: The integrated document retrieval method proposed in the paper can combine the entity index based on the general ontology with domain ontology and the keyword index. Our result verified the effectiveness of the combined index strategy.

Building a Project Memory Using Semantic Design Rationale Process

In the proposal, a construction project memory process based on the semantic annotation is presented. A project Mem-ory concerns the representation and the identification of the experience acquired during projects realization. The main feature of this approach is that the semantic annotation is used to build a continuous semantic design rationale process. We propose in this paper, a semantic traceability in four stages (identifying, structuring, annotating and integrating). The identification and the structuring phases use a model called Extended Marguerite model which fully considers the objectives of the project memory. The annotation phase exploits the results of precedent phase to prepare the final phase. Examples are presented from a case study in an Algerian firm called ENMTP. The architecture supporting the modelling engine is presented. Finally, an evaluation of the degree of the semantic annotation brought by proposed process is given.

基于可调场景语义标注范围的家庭室内语义地图构建

针对家庭室内环境语义地图建图速度较慢和在门口场景语义标注易出现错误等问题,提出一种基于可调场景语义标注范围的家庭室内语义地图构建方法。首先根据YOLOv5s识别的物体大小赋予相应的场景置信度,基于该场景置信度设置阈值使得语义标注范围限制在机器人当前所在区域,确保场景切换时语义标注范围不会立即改变。然后基于人工势场虚拟力“引力斥力”原理,实现语义标注范围的扩大或缩小。最后结合阈值和动态语义标注范围,避免在门口场景中出现语义标注错误。实验结果表明:与Places205-VGG16神经网络建立家庭室内语义地图相比,所提方法平均效率和平均精准率分别提升了11.0%和7.8%,在家庭室内环境中具有一定的优越性。

融合事件和情感的图像语义描述框架研究

[目的/意义]针对图像组织和检索过程中存在的语义缺失和不完整性问题,提出一个面向社会化媒体中的图像语义描述框架,旨在丰富现有的图像描述理论体系,提高图像的检索效率和利用率,为实现自动化的图像语义标注提供参考。[方法/过程]首先,调研分析国内外有关图像描述的研究进展,总结现有的图像描述和标注理论、元数据规范和相关技术方法;其次,在此理论基础上,针对社会化媒体图像领域,构建社会化媒体图像语义描述框架,并详细阐述语义层次及其相互关系。最后,通过人物图像和风景图像实例描述验证图像语义描述框架的可行性。[结果/结论]人物图像和风景图像描述实例结果表明,图像语义描述框架可通过各层之间的语义关联消除图像描述中的“语义鸿沟”,实现对图像外部特征和内容特征的多侧面、多维度、多层次的结构化和语义化描述,具有较强的可移植性和灵活性。

Semantic Relation Annotation for Biomedical Text Mining Based on Recursive Directed Graph

In this paper we propose a novel model ＂recursive directed graph＂ based on feature structure, and apply it to represent the semantic relations of postpositive attributive structures in biomedical texts. The usages of postpositive attributive are complex and variable, especially three categories： present participle phrase, past participle phrase, and preposition phrase as postpositire attributive, which always bring the difficulties of automatic parsing. We summarize these categories and annotate the semantic information. Compared with dependency structure, feature structure, being recursive directed graph, enhances semantic information extraction in biomedical field. The annotation results show that recursive directed graph is more suitable to extract complex semantic relations for biomedical text mining.

2D Correlative-Chain Conditional Random Fields for Semantic Annotation of Web Objects

Semantic annotation of Web objects is a key problem for Web information extraction. The Web contains an abundance of useful semi-structured information about real world objects, and the empirical study shows that strong two-dimensional sequence characteristics and correlative characteristics exist for Web information about objects of the same type across different Web sites. Conditional Random Fields （CRFs） are the state-of-the-art approaches taking the sequence characteristics to do better labeling. However, as the appearance of correlative characteristics between Web object elements, previous CRFs have their limitations for semantic annotation of Web objects and cannot deal with the long distance dependencies between Web object elements efficiently. To better incorporate the long distance dependencies, on one hand, this paper describes long distance dependencies by correlative edges, which are built by making good use of structured information and the characteristics of records from external databases; and on the other hand, this paper presents a two-dimensional Correlative-Chain Conditional Random Fields （2DCC-CRFs） to do semantic annotation of Web objects. This approach extends a classic model, two-dimensional Conditional Random Fields （2DCRFs）, by adding correlative edges. Experimental results using a large number of real-world data collected from diverse domains show that the proposed approach can significantly improve the semantic annotation accuracy of Web objects.

中文医学细粒度知识表示体系与标注语料库构建

面向医学知识的细粒度、可共享性与高精准性的需求,该文提出了中文医学文本知识表示体系,融合了电子病历、医学书籍与专业医学网站文本三个数据来源的医疗知识。该体系包括9类医学实体、60类实体关系。基于此,开发了可操作性高的标注工具,并为每种来源提供了规范标注的医学文本数据,构建了涵盖范围广、一致性高的细粒度标注语料库。4名临床医生对《诊断学》书籍标注了6526个医学实体,4229条关系,标注一致性可达0.974。三个数据源融合后实体数量344475个,关系数量3196787条。该文综述了数据源融合的映射过程、标注细则,分析了各数据源的文本特点并总结标注模式,通过应用场景与文本特点表明医学书籍标注必要性。该文为中文医学语料库构建提供标注规范,并为中文医学实体识别与关系抽取提供语料支持。

结合Hybrid Attention机制和BiLSTM-CRF的汉语否定语义表示及标注

阅读理解中否定是一种复杂的语言现象,其往往会反转情感或态度的极性。因此,正确分析否定语义对语篇理解具有重要意义。现有否定语义分析方法存在两个问题:第一,研究的否定词较少达不到应用目的;第二,目前汉语否定语义标注只是标注整个句子,这无法明确否定语义。针对该问题提出基于汉语框架语义知识库(Chinese FrameNet)进行否定语义角色标注方法。在框架语义学理论指导下结合汉语否定语义特征对已由FrameNet继承的否定框架重新构建;为了解决捕捉长距离信息以及句法特征问题,提出一种基于Hybrid Attention机制的BiLSTMCRF语义角色标注模型,其中,Hybrid Attention机制层将局部注意与全局注意结合准确表示句子中的否定语义,BiLSTM网络层自动学习并提取语句上下文信息,CRF层预测最优否定语义角色标签。经过比对验证,该模型能够有效提取出含有否定语义信息,在否定语义框架数据集上F1值达到89.82%。