Annotation Techniques Research Articles

Cohesion, Adhesion and Incoherence: Magazine Production with a Flickr Special Interest Group

Cohesion, Adhesion and Incoherence: Magazine Production with a Flickr Special Interest Group

MAP-based image tag recommendation using a visual folksonomy

Descriptive tags are needed to enable efficient and effective search in vast collections of images. Tag recommendation represents a trade-off between automatic image annotation techniques and manual tagging. In this letter, we formulate image tag recommendation as a maximum a posteriori (MAP) problem, making use of a visual folksonomy. A folksonomy can be seen as a collaboratively created set of metadata for informal social classification. Our experimental results show that the use of a visual folksonomy for image tag recommendation has two significant benefits, compared to a conventional approach using a limited concept vocabulary. First, our tag recommendation technique can make use of an unrestricted and rich concept vocabulary. Second, our approach is able to recommend a higher number of correct tags.

Semantic Annotation for Java.

This paper describes how to use annotation to provide semantic information. The applications include the automatic construction of a GUI so that the user input is constrained to a correct range (guarding the input). Elementary GUI examples include elements for a variety of data types. Given sufficient effort, we envision the annotation technique as a replacement for XML and BeanInfo-based systems. We show that semantic annotation has several intrinsic benefits, geographically colocating constraints with their parameters eases maintenance, enables compile-time checking, and establishes consistent constraint declarations. Semantic annotation is shown to be GUI agnostic (devoid of Swing, SWT, AWT or HTML considerations). We also show how GUI annotation can be considered dangerous. The automatically constructed GUI’s are simple, and of no intellectual merit, other than their construction technique.

Image interpretation: mining the visible and syntactic correlation of annotated words

Automatic web image annotation is a practical and effective way for both web image retrieval and image understanding. However, current annotation techniques make no further investigation of the statement-level syntactic correlation among the annotated words, therefore making it very difficult to render natural language interpretation for images such as “pandas eat bamboo”. In this paper, we propose an approach to interpret image semantics through mining the visible and textual information hidden in images. This approach mainly consists of two parts: first the annotated words of target images are ranked according to two factors, namely the visual correlation and the pairwise co-occurrence; then the statement-level syntactic correlation among annotated words is explored and natural language interpretation for the target image is obtained. Experiments conducted on real-world web images show the effectiveness of the proposed approach.

A comprehensive assessment of N-terminal signal peptides prediction methods

BackgroundAmino-terminal signal peptides (SPs) are short regions that guide the targeting of secretory proteins to the correct subcellular compartments in the cell. They are cleaved off upon the passenger protein reaching its destination. The explosive growth in sequencing technologies has led to the deposition of vast numbers of protein sequences necessitating rapid functional annotation techniques, with subcellular localization being a key feature. Of the myriad software prediction tools developed to automate the task of assigning the SP cleavage site of these new sequences, we review here, the performance and reliability of commonly used SP prediction tools.ResultsThe available signal peptide data has been manually curated and organized into three datasets representing eukaryotes, Gram-positive and Gram-negative bacteria. These datasets are used to evaluate thirteen prediction tools that are publicly available. SignalP (both the HMM and ANN versions) maintains consistency and achieves the best overall accuracy in all three benchmarking experiments, ranging from 0.872 to 0.914 although other prediction tools are narrowing the performance gap.ConclusionThe majority of the tools evaluated in this study encounter no difficulty in discriminating between secretory and non-secretory proteins. The challenge clearly remains with pinpointing the correct SP cleavage site. The composite scoring schemes employed by SignalP may help to explain its accuracy. Prediction task is divided into a number of separate steps, thus allowing each score to tackle a particular aspect of the prediction.

Enhancing availability of learning resources on organic agriculture and agroecology

PurposeThe purpose of this paper is to describe the provision of existing learning object repositories with enhanced forms of describing digital resources on organic agriculture and agroecology.Design/methodology/approachThe approach followed was to investigate non‐invasive techniques for semantic annotation of learning objects, for which use was made of two tools. The first tool was a software application for the automated classification of learning resources stored in public learning object repositories. The second tool was an ontology in OWL derived from the knowledge in the Agrovoc thesaurus.FindingsCurrent digital repositories for educational resources and open access archives provide scholars with a number of features, such as the ability to search for materials according to given criteria, or to retrieve the full content of those materials from the repository. Many provide advanced features as well, such as browsing, assessing and collaboratively peer reviewing learning resources, but at the cost of using the specific tools and interfaces provided by each repository.Research limitations/implicationsThis research is part of the EU‐funded project Organic.Edunet, aimed at facilitating access, usage and exploitation of digital educational content related to organic agriculture and agroecology (OA&AE). Consequently, knowledge representation, thesauri and the educational resources reported herein are deliberately focused on the OA&AE domain, even though the concepts and techniques utilized may be easily applied in other contexts.Originality/valueThe paper describes two new approaches aimed at enhancing availability of learning resources: the potential use of ontologies for the description of learning resources, and the full use of the classification category in the IEEE LOM metadata standard.

Image annotation techniques based on feature selection for class-pairs

Image annotation technique can be formulated as a multi-class classification problem, which can be solved by the ensemble of multiple class-pair classifiers. Support vector machine (SVM) classifiers based on optimal class-pair feature subsets from the multimedia content description interface (MPEG-7) standard are used as the class-pair classifiers. We use a binary-coded chromosome genetic algorithm (GA) to select optimal class-pair feature subsets, and a bi-coded chromosome GA to simultaneously select optimal class-pair feature subsets and corresponding optimal weight subsets, i.e. optimal class-pair weighted feature subsets. We consider two kinds of methods for class-pair feature selection: a common optimal (or weighted) feature subset is selected for all the class-pairs, and an individual optimal (or weighted) feature subset is selected for each class-pair respectively. Majority voting scheme is used to combine the class-pair SVM classifiers. The experiments are performed on two different image sets to validate the performance of our image annotation techniques.

Cerno: Light-weight tool support for semantic annotation of textual documents

Enrichment of text documents with semantic metadata reflecting their meaning facilitates document organization, indexing and retrieval. However, most web data remain unstructured because of the difficulty and the cost of manually annotating text. In this work, we present Cerno, a framework for semi-automatic semantic annotation of textual documents according to a domain-specific semantic model. The proposed framework is founded on light-weight techniques and tools intended for legacy code analysis and markup. To illustrate the feasibility of our proposal, we report experimental results of its application to two different domains. These results suggest that light-weight semi-automatic techniques for semantic annotation are feasible, require limited human effort for adaptation to a new domain, and demonstrate markup quality comparable with state-of-the-art methods.

Knowledge-assisted visualization of seismic data

We present novel techniques for knowledge-assisted annotation and computer-assisted interpretation of seismic data for oil and gas exploration. We describe the existing procedure for oil and gas search which consists of manually extracting information from seismic data and then aggregating it into knowledge in a detail-oriented bottom-up approach. We then point out the weaknesses of this approach and propose how to improve on it by introducing a holistic computer-assisted top-down approach intended as a preparation step enabling a quicker, more focused and accurate bottom-up interpretation. The top-down approach also enables early representations of hypotheses and knowledge using domain-specific textures for annotating the data. Finally we discuss how these annotations can be extended to 3D for volumetric annotations.

OntoPortal: An ontology-supported portal architecture with linguistically enhanced and focused crawler technologies

This paper proposed the techniques of ontology and linguistics to develop a fully-automatic annotation technique, coupling with an automatic ontology construction method, could play a key role in the development of Semantic Portals. An ontology-supported portal architecture: OntoPortal was proposed according to this technique, in which three internal components Portal Interface, Semantic Portal, and OntoCrawler was integrated to rapidly and precisely collect information on Internet and capture true user’s intention and accordingly provide high-quality query answers to meet the user requests. This paper also demonstrated the OntoPortal prototype which defined how a semantic portal is interacting with the user by providing five different types of interaction patterns such as including keyword search, synonym search, POS (Part-of-Speech)-constrained keyword search, natural language query, and semantic index search. The preliminary experiment outcomes proved the technology proposed in this paper to be able to really up-rise the precision and recall rates of webpage searching and accordingly showed that it can indeed retrieve better semantic-directed information to meet user requests.

Building neuroinformatic data collections with respect to re-usabilityand sustainability

Event Abstract Back to Event Building neuroinformatic data collections with respect to re-usabilityand sustainability Simon Rerucha1* and Ondrej Kotek1 1 Masaryk University, Faculty of Informatics, Czechia During the research on the field neuroinformatics a large amounts of experimental data are created. These data often contains valuable information that might be re-used withing other research on similar fields, nonetheless the data are often insufficiently organized and described - that factor makes repeated use difficult. Our effort is aimed at reduction of costs to data exploitation ratio, the principal idea is that by spending of certain effort on data organization beyond the scope of their primary use can significantly enhance the value of the data. However the problem is complex and incorporates several aspect, each of which brings different requirements "e.g.data diversity, generic annotation techniques, data sustainability, methods of publication and interchange and finally the motivation of the data sets creators. This contribution proposes a series of methods and recommendation on building reusable and sustainable data collection in the scope of research within Czech National Node for Neuroinformatics (CNNN), but with respect to standards within international neroinformatic community. It is developed on the basis of particular experience with the research within CNNN and the outcomes of the INCF efforts.

A clustering‐based semi‐automated technique to build cultural ontologies

AbstractThis article presents and validates a clustering‐based method for creating cultural ontologies for community‐oriented information systems. The introduced semiautomated approach merges distributed annotation techniques, or subjective assessments of similarities between cultural categories, with established clustering methods to produce “cognate” ontologies. This approach is validated against a locally authentic ethnographic method, involving direct work with communities for the design of “fluid” ontologies. The evaluation is conducted with of a set of Native American communities located in San Diego County (CA, US). The principal aim of this research is to discover whether distributing the annotation process among isolated respondents would enable ontology hierarchies to be created that are similar to those that are crafted according to collaborative ethnographic processes, found to be effective in generating continuous usage across several studies. Our findings suggest that the proposed semiautomated solution best optimizes among issues of interoperability and scalability, deemphasized in the fluid ontology approach, and sustainable usage.

Automatic image annotation using visual content and folksonomies

Automatic image annotation is an important and challenging task, and becomes increasingly necessary when managing large image collections. This paper describes techniques for automatic image annotation that take advantage of collaboratively annotated image databases, so called visual folksonomies. Our approach applies two techniques based on image analysis: First, classification annotates images with a controlled vocabulary and second tag propagation along visually similar images. The latter propagates user generated, folksonomic annotations and is therefore capable of dealing with an unlimited vocabulary. Experiments with a pool of Flickr images demonstrate the high accuracy and efficiency of the proposed methods in the task of automatic image annotation. Both techniques were applied in the prototypical tag recommender "tagr".

Automatic Semantic Annotation of Real-World Web Images

As the number of web images is increasing at a rapid rate, searching them semantically presents a significant challenge. Many raw images are constantly uploaded with little meaningful direct annotations of semantic content, limiting their search and discovery. In this paper, we present a semantic annotation technique based on the use of image parametric dimensions and metadata. Using decision trees and rule induction, we develop a rule-based approach to formulate explicit annotations for images fully automatically, so that by the use of our method, semantic query such as " sunset by the sea in autumn in New York" can be answered and indexed purely by machine. Our system is evaluated quantitatively using more than 100,000 web images. Experimental results indicate that this approach is able to deliver highly competent performance, attaining good recall and precision rates of sometimes over 80%. This approach enables a new degree of semantic richness to be automatically associated with images which previously can only be performed manually.

ProSOM: core promoter prediction based on unsupervised clustering of DNA physical profiles

Motivation: More and more genomes are being sequenced, and to keep up with the pace of sequencing projects, automated annotation techniques are required. One of the most challenging problems in genome annotation is the identification of the core promoter. Because the identification of the transcription initiation region is such a challenging problem, it is not yet a common practice to integrate transcription start site prediction in genome annotation projects. Nevertheless, better core promoter prediction can improve genome annotation and can be used to guide experimental work.Results: Comparing the average structural profile based on base stacking energy of transcribed, promoter and intergenic sequences demonstrates that the core promoter has unique features that cannot be found in other sequences. We show that unsupervised clustering by using self-organizing maps can clearly distinguish between the structural profiles of promoter sequences and other genomic sequences. An implementation of this promoter prediction program, called ProSOM, is available and has been compared with the state-of-the-art. We propose an objective, accurate and biologically sound validation scheme for core promoter predictors. ProSOM performs at least as well as the software currently available, but our technique is more balanced in terms of the number of predicted sites and the number of false predictions, resulting in a better all-round performance. Additional tests on the ENCODE regions of the human genome show that 98% of all predictions made by ProSOM can be associated with transcriptionally active regions, which demonstrates the high precision.Availability: Predictions for the human genome, the validation datasets and the program (ProSOM) are available upon request.Contact: yves.vandepeer@psb.ugent.be

Wide-Coverage Deep Statistical Parsing Using Automatic Dependency Structure Annotation

A number of researchers have recently conducted experiments comparing “deep” hand-crafted wide-coverage with “shallow” treebank- and machine-learning-based parsers at the level of dependencies, using simple and automatic methods to convert tree output generated by the shallow parsers into dependencies. In this article, we revisit such experiments, this time using sophisticated automatic LFG f-structure annotation methodologies with surprising results. We compare various PCFG and history-based parsers to find a baseline parsing system that fits best into our automatic dependency structure annotation technique. This combined system of syntactic parser and dependency structure annotation is compared to two hand-crafted, deep constraint-based parsers, RASP and XLE. We evaluate using dependency-based gold standards and use the Approximate Randomization Test to test the statistical significance of the results. Our experiments show that machine-learning-based shallow grammars augmented with sophisticated automatic dependency annotation technology outperform hand-crafted, deep, wide-coverage constraint grammars. Currently our best system achieves an f-score of 82.73% against the PARC 700 Dependency Bank, a statistically significant improvement of 2.18% over the most recent results of 80.55% for the hand-crafted LFG grammar and XLE parsing system and an f-score of 80.23% against the CBS 500 Dependency Bank, a statistically significant 3.66% improvement over the 76.57% achieved by the hand-crafted RASP grammar and parsing system.

Influence of contextual information in emotion annotation for spoken dialogue systems

In this paper, we study the impact of considering context information for the annotation of emotions. Concretely, we propose the inclusion of the history of user–system interaction and the neutral speaking style of users. A new method to automatically include both sources of information has been developed making use of novel techniques for acoustic normalization and dialogue context annotation. We have carried out experiments with a corpus extracted from real human interactions with a spoken dialogue system. Results show that the performance of non-expert human annotators and machine-learned classifications are both affected by contextual information. The proposed method allows the annotation of more non-neutral emotions and yields values closer to maximum agreement rates for non-expert human annotation. Moreover, automatic classification accuracy improves by 29.57% compared to the classical approach based only on acoustic features.

Exploring the extremes of sequence/structure space with ensemble fold recognition in the program Phyre

Structural and functional annotation of the large and growing database of genomic sequences is a major problem in modern biology. Protein structure prediction by detecting remote homology to known structures is a well-established and successful annotation technique. However, the broad spectrum of evolutionary change that accompanies the divergence of close homologues to become remote homologues cannot easily be captured with a single algorithm. Recent advances to tackle this problem have involved the use of multiple predictive algorithms available on the Internet. Here we demonstrate how such ensembles of predictors can be designed in-house under controlled conditions and permit significant improvements in recognition by using a concept taken from protein loop energetics and applying it to the general problem of 3D clustering. We have developed a stringent test that simulates the situation where a protein sequence of interest is submitted to multiple different algorithms and not one of these algorithms can make a confident (95%) correct assignment. A method of meta-server prediction (Phyre) that exploits the benefits of a controlled environment for the component methods was implemented. At 95% precision or higher, Phyre identified 64.0% of all correct homologous query-template relationships, and 84.0% of the individual test query proteins could be accurately annotated. In comparison to the improvement that the single best fold recognition algorithm (according to training) has over PSI-Blast, this represents a 29.6% increase in the number of correct homologous query-template relationships, and a 46.2% increase in the number of accurately annotated queries. It has been well recognised in fold prediction, other bioinformatics applications, and in many other areas, that ensemble predictions generally are superior in accuracy to any of the component individual methods. However there is a paucity of information as to why the ensemble methods are superior and indeed this has never been systematically addressed in fold recognition. Here we show that the source of ensemble power stems from noise reduction in filtering out false positive matches. The results indicate greater coverage of sequence space and improved model quality, which can consequently lead to a reduction in the experimental workload of structural genomics initiatives.

Multimedia enriched ontologies for video digital libraries

The development of appropriate tools and solutions to support effective access to video content is one of the main challenges for video digital libraries. Different techniques for manual and automatic annotation and retrieval have been proposed in recent years. It is a common practice to use linguistic ontologies for video annotation and retrieval: video elements are classified by establishing relationships between video contents and linguistic terms that identify domain concepts at different abstraction levels. However, although linguistic terms are appropriate to distinguish event and object categories, they are inadequate when they must describe specific or complex patterns of events or video entities. Instead, in these cases, pattern specifications can be better expressed using visual prototypes, either images or video clips, that capture the essence of the event or entity. High level concepts, expressed trough linguistic terms, and patterns specification, represented by visual prototypes, can be both organized into new extended ontologies where images or video clips are added to the ontologies as specification of linguistic terms. This paper presents algorithms and techniques that employ enriched ontologies for video annotation and retrieval, and discusses a solution for their implementation for the soccer video domain. An unsupervised clustering method is proposed in order to create multimedia enriched ontologies by defining visual prototypes that represent specific patterns of highlights and adding them as visual concepts to the ontology. An algorithm that uses multimedia enriched ontologies to perform automatic soccer video annotation is proposed and results for typical highlights are presented. Annotation is performed associating occurrences of events, or entities, to higher level concepts by checking their similarity to visual concepts that are hierarchically linked to higher level semantics, using a dynamic programming approach. Usage of reasoning on the ontology is shown, to create complex queries that comprise visual prototypes of actions, their temporal evolution and relations.

BioCAD: an information fusion platform for bio-network inference and analysis

BackgroundAs systems biology has begun to draw growing attention, bio-network inference and analysis have become more and more important. Though there have been many efforts for bio-network inference, they are still far from practical applications due to too many false inferences and lack of comprehensible interpretation in the biological viewpoints. In order for applying to real problems, they should provide effective inference, reliable validation, rational elucidation, and sufficient extensibility to incorporate various relevant information sources.ResultsWe have been developing an information fusion software platform called BioCAD. It is utilizing both of local and global optimization for bio-network inference, text mining techniques for network validation and annotation, and Web services-based workflow techniques. In addition, it includes an effective technique to elucidate network edges by integrating various information sources. This paper presents the architecture of BioCAD and essential modules for bio-network inference and analysis.ConclusionBioCAD provides a convenient infrastructure for network inference and network analysis. It automates series of users' processes by providing data preprocessing tools for various formats of data. It also helps inferring more accurate and reliable bio-networks by providing network inference tools which utilize information from distinct sources. And it can be used to analyze and validate the inferred bio-networks using information fusion tools.