Academic literature on the topic 'Constraints annotation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Constraints annotation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Constraints annotation":
1
SAMPSON, GEOFFREY, and ANNA BABARCZY. "Definitional and human constraints on structural annotation of English." Natural Language Engineering 14, no. 4 (October 2008): 471–94. http://dx.doi.org/10.1017/s1351324908004695.
Abstract:
AbstractThe limits on predictability and refinement of English structural annotation are examined by comparing independent annotations, by experienced analysts using the same detailed published guidelines, of a common sample of written texts. Three conclusions emerge. First, while it is not easy to define watertight boundaries between the categories of a comprehensive structural annotation scheme, limits on inter-annotator agreement are in practice set more by the difficulty of conforming to a well-defined scheme than by the difficulty of making a scheme well defined. Secondly, although usage is often structurally ambiguous, commonly the alternative analyses are logical distinctions without a practical difference – which raises questions about the role of grammar in human linguistic behaviour. Finally, one specific area of annotation is strikingly more problematic than any other area examined, though this area (classifying the functions of clause-constituents) seems a particularly significant one for human language use. These findings should be of interest both to computational linguists and to students of language as an aspect of human cognition.
2
Anderson, Matthew, Salman Sadiq, Muzammil Nahaboo Solim, Hannah Barker, David H. Steel, Maged Habib, and Boguslaw Obara. "Biomedical Data Annotation: An OCT Imaging Case Study." Journal of Ophthalmology 2023 (August 22, 2023): 1–9. http://dx.doi.org/10.1155/2023/5747010.
Abstract:
In ophthalmology, optical coherence tomography (OCT) is a widely used imaging modality, allowing visualisation of the structures of the eye with objective and quantitative cross-sectional three-dimensional (3D) volumetric scans. Due to the quantity of data generated from OCT scans and the time taken for an ophthalmologist to inspect for various disease pathology features, automated image analysis in the form of deep neural networks has seen success for the classification and segmentation of OCT layers and quantification of features. However, existing high-performance deep learning approaches rely on huge training datasets with high-quality annotations, which are challenging to obtain in many clinical applications. The collection of annotations from less experienced clinicians has the potential to alleviate time constraints from more senior clinicians, allowing faster data collection of medical image annotations; however, with less experience, there is the possibility of reduced annotation quality. In this study, we evaluate the quality of diabetic macular edema (DME) intraretinal fluid (IRF) biomarker image annotations on OCT B-scans from five clinicians with a range of experience. We also assess the effectiveness of annotating across multiple sessions following a training session led by an expert clinician. Our investigation shows a notable variance in annotation performance, with a correlation that depends on the clinician’s experience with OCT image interpretation of DME, and that having multiple annotation sessions has a limited effect on the annotation quality.
3
Lin, Jia-Wen, Feng Lu, Tai-Chen Lai, Jing Zou, Lin-Ling Guo, Zhi-Ming Lin, and Li Li. "Meibomian glands segmentation in infrared images with limited annotation." International Journal of Ophthalmology 17, no. 3 (March 18, 2024): 401–7. http://dx.doi.org/10.18240/ijo.2024.03.01.
Abstract:
AIM: To investigate a pioneering framework for the segmentation of meibomian glands (MGs), using limited annotations to reduce the workload on ophthalmologists and enhance the efficiency of clinical diagnosis. METHODS: Totally 203 infrared meibomian images from 138 patients with dry eye disease, accompanied by corresponding annotations, were gathered for the study. A rectified scribble-supervised gland segmentation (RSSGS) model, incorporating temporal ensemble prediction, uncertainty estimation, and a transformation equivariance constraint, was introduced to address constraints imposed by limited supervision information inherent in scribble annotations. The viability and efficacy of the proposed model were assessed based on accuracy, intersection over union (IoU), and dice coefficient. RESULTS: Using manual labels as the gold standard, RSSGS demonstrated outcomes with an accuracy of 93.54%, a dice coefficient of 78.02%, and an IoU of 64.18%. Notably, these performance metrics exceed the current weakly supervised state-of-the-art methods by 0.76%, 2.06%, and 2.69%, respectively. Furthermore, despite achieving a substantial 80% reduction in annotation costs, it only lags behind fully annotated methods by 0.72%, 1.51%, and 2.04%. CONCLUSION: An innovative automatic segmentation model is developed for MGs in infrared eyelid images, using scribble annotation for training. This model maintains an exceptionally high level of segmentation accuracy while substantially reducing training costs. It holds substantial utility for calculating clinical parameters, thereby greatly enhancing the diagnostic efficiency of ophthalmologists in evaluating meibomian gland dysfunction.
4
Grác, Marek, Markéta Masopustová, and Marie Valíčková. "Affordable Annotation of the Mobile App Reviews." Journal of Linguistics/Jazykovedný casopis 70, no. 2 (December 1, 2019): 491–97. http://dx.doi.org/10.2478/jazcas-2019-0077.
Abstract:
Abstract This paper focuses on the use-case study of the annotation of the mobile app reviews from Google Play and Apple Store. These annotations of sentiment polarity were created for later use in the automatic processing based on machine learning. This should solve some of the problems encountered in the previous analyses of the Czech language where data assumptions play a greater role than annotation itself (due to the financial constraints). Our proposal shows that some of the assumptions used for English do not apply to Czech and that it is possible to annotate such data without extensive financing.
5
Olivier, Brett G., and Frank T. Bergmann. "The Systems Biology Markup Language (SBML) Level 3 Package: Flux Balance Constraints." Journal of Integrative Bioinformatics 12, no. 2 (June 1, 2015): 660–90. http://dx.doi.org/10.1515/jib-2015-269.
Abstract:
Summary Constraint-based modeling is a well established modelling methodology used to analyze and study biological networks on both a medium and genome scale. Due to their large size, genome scale models are typically analysed using constraint-based optimization techniques. One widely used method is Flux Balance Analysis (FBA) which, for example, requires a modelling description to include: the definition of a stoichiometric matrix, an objective function and bounds on the values that fluxes can obtain at steady state.The Flux Balance Constraints (FBC) Package extends SBML Level 3 and provides a standardized format for the encoding, exchange and annotation of constraint-based models. It includes support for modelling concepts such as objective functions, flux bounds and model component annotation that facilitates reaction balancing. The FBC package establishes a base level for the unambiguous exchange of genome-scale, constraint-based models, that can be built upon by the community to meet future needs (e. g. by extending it to cover dynamic FBC models).
6
Luo, Yuan, and Peter Szolovits. "Efficient Queries of Stand-off Annotations for Natural Language Processing on Electronic Medical Records." Biomedical Informatics Insights 8 (January 2016): BII.S38916. http://dx.doi.org/10.4137/bii.s38916.
Abstract:
In natural language processing, stand-off annotation uses the starting and ending positions of an annotation to anchor it to the text and stores the annotation content separately from the text. We address the fundamental problem of efficiently storing stand-off annotations when applying natural language processing on narrative clinical notes in electronic medical records (EMRs) and efficiently retrieving such annotations that satisfy position constraints. Efficient storage and retrieval of stand-off annotations can facilitate tasks such as mapping unstructured text to electronic medical record ontologies. We first formulate this problem into the interval query problem, for which optimal query/update time is in general logarithm. We next perform a tight time complexity analysis on the basic interval tree query algorithm and show its nonoptimality when being applied to a collection of 13 query types from Allen's interval algebra. We then study two closely related state-of-the-art interval query algorithms, proposed query reformulations, and augmentations to the second algorithm. Our proposed algorithm achieves logarithmic time stabbing-max query time complexity and solves the stabbing-interval query tasks on all of Allen's relations in logarithmic time, attaining the theoretic lower bound. Updating time is kept logarithmic and the space requirement is kept linear at the same time. We also discuss interval management in external memory models and higher dimensions.
7
ISMAIL, MOHAMED MAHER BEN, and OUIEM BCHIR. "AUTOMATIC IMAGE ANNOTATION BASED ON SEMI-SUPERVISED CLUSTERING AND MEMBERSHIP-BASED CROSS MEDIA RELEVANCE MODEL." International Journal of Pattern Recognition and Artificial Intelligence 26, no. 06 (September 2012): 1255009. http://dx.doi.org/10.1142/s0218001412550099.
Abstract:
In this paper, we propose a system for automatic image annotation that has two main components. The first component consists of a novel semi-supervised possibilistic clustering and feature weighting algorithm based on robust modeling of the generalized Dirichlet (GD) finite mixture. This algorithm is used to group image regions into prototypical region clusters that summarize the training data and can be used as the basis of annotating new test images. The constraints consist of pairs of image regions that should not be included in the same cluster. These constraints are deduced from the irrelevance of all concepts annotating the training images to help in guiding the clustering process. The second component of our system consists of a probabilistic model that relies on the possibilistic membership degrees, generated by the clustering algorithm, to annotate unlabeled images. The proposed system was implemented and tested on a data set that include thousands of images using four-fold cross validation.
8
BABARCZY, ANNA, JOHN CARROLL, and GEOFFREY SAMPSON. "Definitional, personal, and mechanical constraints on part of speech annotation performance." Natural Language Engineering 12, no. 1 (December 6, 2005): 77–90. http://dx.doi.org/10.1017/s1351324905003803.
Abstract:
For one aspect of grammatical annotation, part-of-speech tagging, we investigate experimentally whether the ceiling on accuracy stems from limits to the precision of tag definition or limits to analysts' ability to apply precise definitions, and we examine how analysts' performance is affected by alternative types of semi-automatic support. We find that, even for analysts very well-versed in a part-of-speech tagging scheme, human ability to conform to the scheme is a more serious constraint than precision of scheme definition. We also find that although semi-automatic techniques can greatly increase speed relative to manual tagging, they have little effect on accuracy, either positively (by suggesting valid candidate tags) or negatively (by lending an appearance of authority to incorrect tag assignments). On the other hand, it emerges that there are large differences between individual analysts with respect to usability of particular types of semi-automatic support.
9
Ge, Hongwei, Zehang Yan, Jing Dou, Zhen Wang, and ZhiQiang Wang. "A Semisupervised Framework for Automatic Image Annotation Based on Graph Embedding and Multiview Nonnegative Matrix Factorization." Mathematical Problems in Engineering 2018 (June 27, 2018): 1–11. http://dx.doi.org/10.1155/2018/5987906.
Abstract:
Automatic image annotation is for more accurate image retrieval and classification by assigning labels to images. This paper proposes a semisupervised framework based on graph embedding and multiview nonnegative matrix factorization (GENMF) for automatic image annotation with multilabel images. First, we construct a graph embedding term in the multiview NMF based on the association diagrams between labels for semantic constraints. Then, the multiview features are fused and dimensions are reduced based on multiview NMF algorithm. Finally, image annotation is achieved by using the new features through a KNN-based approach. Experiments validate that the proposed algorithm has achieved competitive performance in terms of accuracy and efficiency.
10
Nursimulu, Nirvana, Alan M. Moses, and John Parkinson. "Architect: A tool for aiding the reconstruction of high-quality metabolic models through improved enzyme annotation." PLOS Computational Biology 18, no. 9 (September 8, 2022): e1010452. http://dx.doi.org/10.1371/journal.pcbi.1010452.
Abstract:
Constraint-based modeling is a powerful framework for studying cellular metabolism, with applications ranging from predicting growth rates and optimizing production of high value metabolites to identifying enzymes in pathogens that may be targeted for therapeutic interventions. Results from modeling experiments can be affected at least in part by the quality of the metabolic models used. Reconstructing a metabolic network manually can produce a high-quality metabolic model but is a time-consuming task. At the same time, current methods for automating the process typically transfer metabolic function based on sequence similarity, a process known to produce many false positives. We created Architect, a pipeline for automatic metabolic model reconstruction from protein sequences. First, it performs enzyme annotation through an ensemble approach, whereby a likelihood score is computed for an EC prediction based on predictions from existing tools; for this step, our method shows both increased precision and recall compared to individual tools. Next, Architect uses these annotations to construct a high-quality metabolic network which is then gap-filled based on likelihood scores from the ensemble approach. The resulting metabolic model is output in SBML format, suitable for constraints-based analyses. Through comparisons of enzyme annotations and curated metabolic models, we demonstrate improved performance of Architect over other state-of-the-art tools, notably with higher precision and recall on the eukaryote C. elegans and when compared to UniProt annotations in two bacterial species. Code for Architect is available at https://github.com/ParkinsonLab/Architect. For ease-of-use, Architect can be readily set up and utilized using its Docker image, maintained on Docker Hub.
Dissertations / Theses on the topic "Constraints annotation":
1
Schild, Erwan. "De l’importance de valoriser l’expertise humaine dans l’annotation : application à la modélisation de textes en intentions à l’aide d’un clustering interactif." Electronic Thesis or Diss., Université de Lorraine, 2024. http://www.theses.fr/2024LORR0024.
Abstract:
La tâche d'annotation, nécessaire à l'entraînement d'assistants conversationnels, fait habituellement appel à des experts du domaine à modéliser. Toutefois, l'annotation de données est connue pour être une tâche difficile en raison de sa complexité et sa subjectivité : elle nécessite par conséquent de solides compétences analytiques dans le but de modéliser les textes en intention de dialogue. De ce fait, la plupart des projets d'annotation choisissent de former les experts aux tâches d'analyse pour en faire des "super-experts". Dans cette thèse, nous avons plutôt décidé mettre l'accent sur les connaissances réelles des experts en proposant une nouvelle méthode d'annotation basée sur un Clustering Interactif. Celle-ci se base sur une coopération Homme/Machine, où la machine réalise un clustering pour proposer une base initiale d'apprentissage, et où l'expert annote des contraintes MUST-LINK ou CANNOT-LINK entre les données pour affiner itérativement la base d'apprentissage proposée. Une telle annotation présente l'avantage d'être plus instinctive, car les experts peuvent associer ou différencier les données en fonction de la similarité de leur cas d'usage, permettant ainsi de traiter les données comme ils le feraient professionnellement au quotidien. Au cours de nos études, nous avons pu montrer que cette méthode diminuait sensiblement la complexité de conception d'une base d'apprentissage, réduisant notamment la nécessité de formation des experts intervenant dans un projet d'annotation. Nous proposons une implémentation technique de cette méthode (algorithmes et interface graphique associée), ainsi qu'une étude des paramètres optimaux pour obtenir une base d'apprentissage cohérente en un minimum d'annotation. Nous réalisons également une étude de coûts (techniques et humains) permettant de confirmer que l'utilisation d'une telle méthode est réaliste dans un cadre industriel. De plus, afin que la méthode atteigne son plein potentiel, nous fournissons un ensemble de conseils, notamment : (1) des recommandations visant à cadrer la stratégie d'annotation, (2) une aide à l'identification et à la résolution des divergences d'opinion entre annotateurs, (3) des indicateurs de rentabilité pour chaque intervention de l'expert, et (4) des méthodes d'analyse de la pertinence de la base d'apprentissage en cours de construction. En conclusion, cette thèse offre une approche innovante pour concevoir une base d'apprentissage d'un assistant conversationnel, permettant d'impliquer les experts du domaine métier pour leurs vraies connaissances, tout en leur demandant un minimum de compétences analytiques et techniques. Ces travaux ouvrent ainsi la voie à des méthodes plus accessibles pour la construction de ces assistantsUsually, the task of annotation, used to train conversational assistants, relies on domain experts who understand the subject matter to model. However, data annotation is known to be a challenging task due to its complexity and subjectivity. Therefore, it requires strong analytical skills to model the text in dialogue intention. As a result, most annotation projects choose to train experts in analytical tasks to turn them into "super-experts". In this thesis, we decided instead to focus on the real knowledge of experts by proposing a new annotation method based on Interactive Clustering. This method involves a Human-Machine cooperation, where the machine performs clustering to provide an initial learning base, and the expert annotates MUST-LINK or CANNOT-LINK constraints between the data to iteratively refine the proposed learning base. Such annotation has the advantage of being more instinctive, as experts can associate or differentiate data according to the similarity of their use cases, allowing them to handle the data as they would professionally do on a daily basis. During our studies, we have been able to show that this method significantly reduces the complexity of designing a learning base, notably by reducing the need for training the experts involved in an annotation project. We provide a technical implementation of this method (algorithms and associated graphical interface), as well as a study of optimal parameters to achieve a coherent learning base with minimal annotation. We have also conducted a cost study (both technical and human) to confirm that the use of such a method is realistic in an industrial context. Finally, we provide a set of recommendations to help this method reach its full potential, including: (1) advice aimed at framing the annotation strategy, (2) assistance in identifying and resolving differences of opinion between annotators, (3) rentability indicators for each expert intervention, and (4) methods for analyzing the relevance of the learning base under construction. In conclusion, this thesis provides an innovative approach to design a learning base for a conversational assistant, involving domain experts for their actual knowledge, while requiring a minimum of analytical and technical skills. This work opens the way for more accessible methods for building such assistants
2
Ong, Wai, Trang Vu, Klaus Lovendahl, Jenna Llull, Margrethe Serres, Margaret Romine, and Jennifer Reed. "Comparisons of Shewanella strains based on genome annotations, modeling, and experiments." BioMed Central, 2014. http://hdl.handle.net/10150/610105.
Abstract:
BACKGROUND:Shewanella is a genus of facultatively anaerobic, Gram-negative bacteria that have highly adaptable metabolism which allows them to thrive in diverse environments. This quality makes them an attractive bacterial target for research in bioremediation and microbial fuel cell applications. Constraint-based modeling is a useful tool for helping researchers gain insights into the metabolic capabilities of these bacteria. However, Shewanella oneidensis MR-1 is the only strain with a genome-scale metabolic model constructed out of 21 sequenced Shewanella strains.RESULTS:In this work, we updated the model for Shewanella oneidensis MR-1 and constructed metabolic models for three other strains, namely Shewanella sp. MR-4, Shewanella sp. W3-18-1, and Shewanella denitrificans OS217 which span the genus based on the number of genes lost in comparison to MR-1. We also constructed a Shewanella core model that contains the genes shared by all 21 sequenced strains and a few non-conserved genes associated with essential reactions. Model comparisons between the five constructed models were done at two levels - for wildtype strains under different growth conditions and for knockout mutants under the same growth condition. In the first level, growth/no-growth phenotypes were predicted by the models on various carbon sources and electron acceptors. Cluster analysis of these results revealed that the MR-1 model is most similar to the W3-18-1 model, followed by the MR-4 and OS217 models when considering predicted growth phenotypes. However, a cluster analysis done based on metabolic gene content revealed that the MR-4 and W3-18-1 models are the most similar, with the MR-1 and OS217 models being more distinct from these latter two strains. As a second level of comparison, we identified differences in reaction and gene content which give rise to different functional predictions of single and double gene knockout mutants using Comparison of Networks by Gene Alignment (CONGA). Here, we showed how CONGA can be used to find biomass, metabolic, and genetic differences between models.CONCLUSIONS:We developed four strain-specific models and a general core model that can be used to do various in silico studies of Shewanella metabolism. The developed models provide a platform for a systematic investigation of Shewanella metabolism to aid researchers using Shewanella in various biotechnology applications.
3
Boyd, Adriane Amelia. "Detecting and Diagnosing Grammatical Errors for Beginning Learners of German: From Learner Corpus Annotation to Constraint Satisfaction Problems." The Ohio State University, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=osu1325170396.
4
Wodke, Judith. "Organization and integration of large-scale datasets for designing a metabolic model and re-annotating the genome of mycoplasma pneumoniae." Doctoral thesis, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I, 2013. http://dx.doi.org/10.18452/16699.
Abstract:
Mycoplasma pneumoniae, einer der kleinsten lebenden Organismen, ist ein erfolgversprechender Modellorganismus der Systembiologie um eine komplette lebende Zelle zu verstehen. Wichtig dahingehend ist die Konstruktion mathematischer Modelle, die zelluläre Prozesse beschreiben, indem sie beteiligte Komponenten vernetzen und zugrundeliegende Mechanismen entschlüsseln. Für Mycoplasma pneumoniae wurden genomweite Datensätze für Genomics, Transcriptomics, Proteomics und Metabolomics produziert. Allerdings fehlten ein effizientes Informationsaustauschsystem und mathematische Modelle zur Datenintegration. Zudem waren verschiedene Beobachtungen im metabolischen Verhalten ungeklärt. Diese Dissertation präsentiert einen kombinatorischen Ansatz zur Entwicklung eines metabolischen Modells für Mycoplasma pneumoniae. Zuerst haben wir eine Datenbank, MyMpn, entwickelt, um Zugang zu strukturierten, organisierten Daten zu schaffen. Danach haben wir ein genomweites, Constraint-basiertes metabolisches Modell mit Vorhersagekapazitäten konstruiert und parallel dazu das Metabolome experimentell charakterisiert. Wir haben die Biomasse einer Mycoplasma pneumoniae Zelle definiert, das Netzwerk korrigiert, gezeigt, dass ein Grossteil der produzierten Energie auf zelluläre Homeostase verwendet wird, und das Verhalten unter verschiedenen Wachstumsbedingungen analysiert. Schließlich haben wir manuell das Genom reannotiert. Die Datenbank, obwohl noch nicht öffentlich zugänglich, wird bereits intern für die Analyse experimenteller Daten und die Modellierung genutzt. Die Entdeckung von Kontrollprinzipien des Energiemetabolismus und der Anpassungsfähigkeiten bei Genausfall heben den Einfluss der reduktiven Genomevolution hervor und erleichtert die Entwicklung von Manipulationstechniken und dynamischen Modellen. Überdies haben wir gezeigt, dass die Genomorganisation in Mycoplasma pneumoniae komplexer ist als bisher für möglich gehalten, und 32 neue, noch nicht annotierte Gene entdeckt.Mycoplasma pneumoniae, one of the smallest known self-replicating organisms, is a promising model organism in systems biology when aiming to assess understanding of an entire living cell. One key step towards this goal is the design of mathematical models that describe cellular processes by connecting the involved components to unravel underlying mechanisms. For Mycoplasma pneumoniae, a wealth of genome-wide datasets on genomics, transcriptomics, proteomics, and metabolism had been produced. However, a proper system facilitating information exchange and mathematical models to integrate the different datasets were lacking. Also, different in vivo observations of metabolic behavior remained unexplained. This thesis presents a combinatorial approach to design a metabolic model for Mycoplasma pneumoniae. First, we developed a database, MyMpn, in order to provide access to structured and organized data. Second, we built a predictive, genome-scale, constraint-based metabolic model and, in parallel, we explored the metabolome in vivo. We defined the biomass composition of a Mycoplasma pneumoniae cell, corrected the wiring diagram, showed that a large proportion of energy is dedicated to cellular homeostasis, and analyzed the metabolic behavior under different growth conditions. Finally, we manually re-annotated the genome of Mycoplasma pneumoniae. The database, despite not yet being released to the public, is internally already used for data analysis, and for mathematical modeling. Unraveling the principles governing energy metabolism and adaptive capabilities upon gene deletion highlight the impact of the reductive genome evolution and facilitates the development of engineering tools and dynamic models for metabolic sub-systems. Furthermore, we revealed that the degree of complexity in which the genome of Mycoplasma pneumoniae is organized far exceeds what has been considered possible so far and we identified 32 new, previously not annotated genes.
5
Serrano, Martínez-Santos Nicolás. "Interactive Transcription of Old Text Documents." Doctoral thesis, Universitat Politècnica de València, 2014. http://hdl.handle.net/10251/37979.
Abstract:
Nowadays, there are huge collections of handwritten text documents in libraries
all over the world. The high demand for these resources has led to the creation
of digital libraries in order to facilitate the preservation and provide electronic
access to these documents. However text transcription of these documents im-
ages are not always available to allow users to quickly search information, or
computers to process the information, search patterns or draw out statistics.
The problem is that manual transcription of these documents is an expensive
task from both economical and time viewpoints. This thesis presents a novel ap-
proach for e cient Computer Assisted Transcription (CAT) of handwritten text
documents using state-of-the-art Handwriting Text Recognition (HTR) systems.
The objective of CAT approaches is to e ciently complete a transcription
task through human-machine collaboration, as the e ort required to generate a
manual transcription is high, and automatically generated transcriptions from
state-of-the-art systems still do not reach the accuracy required. This thesis
is centered on a special application of CAT, that is, the transcription of old
text document when the quantity of user e ort available is limited, and thus,
the entire document cannot be revised. In this approach, the objective is to
generate the best possible transcription by means of the user e ort available.
This thesis provides a comprehensive view of the CAT process from feature
extraction to user interaction.
First, a statistical approach to generalise interactive transcription is pro-
posed. As its direct application is unfeasible, some assumptions are made to
apply it to two di erent tasks. First, on the interactive transcription of hand-
written text documents, and next, on the interactive detection of the document
layout.
Next, the digitisation and annotation process of two real old text documents
is described. This process was carried out because of the scarcity of similar
resources and the need of annotated data to thoroughly test all the developed
tools and techniques in this thesis. These two documents were carefully selected
to represent the general di culties that are encountered when dealing with
HTR. Baseline results are presented on these two documents to settle down a
benchmark with a standard HTR system. Finally, these annotated documents
were made freely available to the community. It must be noted that, all the
techniques and methods developed in this thesis have been assessed on these
two real old text documents.
Then, a CAT approach for HTR when user e ort is limited is studied and
extensively tested. The ultimate goal of applying CAT is achieved by putting
together three processes. Given a recognised transcription from an HTR system.
The rst process consists in locating (possibly) incorrect words and employs the
user e ort available to supervise them (if necessary). As most words are not
expected to be supervised due to the limited user e ort available, only a few are
selected to be revised. The system presents to the user a small subset of these
words according to an estimation of their correctness, or to be more precise,
according to their con dence level. Next, the second process starts once these low con dence words have been supervised. This process updates the recogni-
tion of the document taking user corrections into consideration, which improves
the quality of those words that were not revised by the user. Finally, the last
process adapts the system from the partially revised (and possibly not perfect)
transcription obtained so far. In this adaptation, the system intelligently selects
the correct words of the transcription. As results, the adapted system will bet-
ter recognise future transcriptions. Transcription experiments using this CAT
approach show that this approach is mostly e ective when user e ort is low.
The last contribution of this thesis is a method for balancing the nal tran-
scription quality and the supervision e ort applied using our previously de-
scribed CAT approach. In other words, this method allows the user to control
the amount of errors in the transcriptions obtained from a CAT approach. The
motivation of this method is to let users decide on the nal quality of the desired
documents, as partially erroneous transcriptions can be su cient to convey the
meaning, and the user e ort required to transcribe them might be signi cantly
lower when compared to obtaining a totally manual transcription. Consequently,
the system estimates the minimum user e ort required to reach the amount of
error de ned by the user. Error estimation is performed by computing sepa-
rately the error produced by each recognised word, and thus, asking the user to
only revise the ones in which most errors occur.
Additionally, an interactive prototype is presented, which integrates most
of the interactive techniques presented in this thesis. This prototype has been
developed to be used by palaeographic expert, who do not have any background
in HTR technologies. After a slight ne tuning by a HTR expert, the prototype
lets the transcribers to manually annotate the document or employ the CAT ap-
proach presented. All automatic operations, such as recognition, are performed
in background, detaching the transcriber from the details of the system. The
prototype was assessed by an expert transcriber and showed to be adequate and
e cient for its purpose. The prototype is freely available under a GNU Public
Licence (GPL).Serrano Martínez-Santos, N. (2014). Interactive Transcription of Old Text Documents [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/37979
TESIS
6
Guillaumin, Matthieu. "Données multimodales pour l'analyse d'image." Phd thesis, Grenoble, 2010. http://www.theses.fr/2010GRENM048.
Abstract:
La présente thèse s'intéresse à l'utilisation de méta-données textuelles pour l'analyse d'image. Nous cherchons à utiliser ces informations additionelles comme supervision faible pour l'apprentissage de modèles de reconnaissance visuelle. Nous avons observé un récent et grandissant intérêt pour les méthodes capables d'exploiter ce type de données car celles-ci peuvent potentiellement supprimer le besoin d'annotations manuelles, qui sont coûteuses en temps et en ressources. Nous concentrons nos efforts sur deux types de données visuelles associées à des informations textuelles. Tout d'abord, nous utilisons des images de dépêches qui sont accompagnées de légendes descriptives pour s'attaquer à plusieurs problèmes liés à la reconnaissance de visages. Parmi ces problèmes, la vérification de visages est la tâche consistant à décider si deux images représentent la même personne, et le nommage de visages cherche à associer les visages d'une base de données à leur noms corrects. Ensuite, nous explorons des modèles pour prédire automatiquement les labels pertinents pour des images, un problème connu sous le nom d'annotation automatique d'image. Ces modèles peuvent aussi être utilisés pour effectuer des recherches d'images à partir de mots-clés. Nous étudions enfin un scénario d'apprentissage multimodal semi-supervisé pour la catégorisation d'image. Dans ce cadre de travail, les labels sont supposés présents pour les données d'apprentissage, qu'elles soient manuellement annotées ou non, et absentes des données de test. Nos travaux se basent sur l'observation que la plupart de ces problèmes peuvent être résolus si des mesures de similarité parfaitement adaptées sont utilisées. Nous proposons donc de nouvelles approches qui combinent apprentissage de distance, modèles par plus proches voisins et méthodes par graphes pour apprendre, à partir de données visuelles et textuelles, des similarités visuelles spécifiques à chaque problème. Dans le cas des visages, nos similarités se concentrent sur l'identité des individus tandis que, pour les images, elles concernent des concepts sémantiques plus généraux. Expérimentalement, nos approches obtiennent des performances à l'état de l'art sur plusieurs bases de données complexes. Pour les deux types de données considérés, nous montrons clairement que l'apprentissage bénéficie de l'information textuelle supplémentaire résultant en l'amélioration de la performance des systèmes de reconnaissance visuelleThis dissertation delves into the use of textual metadata for image understanding. We seek to exploit this additional textual information as weak supervision to improve the learning of recognition models. There is a recent and growing interest for methods that exploit such data because they can potentially alleviate the need for manual annotation, which is a costly and time-consuming process. We focus on two types of visual data with associated textual information. First, we exploit news images that come with descriptive captions to address several face related tasks, including face verification, which is the task of deciding whether two images depict the same individual, and face naming, the problem of associating faces in a data set to their correct names. Second, we consider data consisting of images with user tags. We explore models for automatically predicting tags for new images, i. E. Image auto-annotation, which can also used for keyword-based image search. We also study a multimodal semi-supervised learning scenario for image categorisation. In this setting, the tags are assumed to be present in both labelled and unlabelled training data, while they are absent from the test data. Our work builds on the observation that most of these tasks can be solved if perfectly adequate similarity measures are used. We therefore introduce novel approaches that involve metric learning, nearest neighbour models and graph-based methods to learn, from the visual and textual data, task-specific similarities. For faces, our similarities focus on the identities of the individuals while, for images, they address more general semantic visual concepts. Experimentally, our approaches achieve state-of-the-art results on several standard and challenging data sets. On both types of data, we clearly show that learning using additional textual information improves the performance of visual recognition systems
7
Guillaumin, Matthieu. "Données multimodales pour l'analyse d'image." Phd thesis, Grenoble, 2010. http://tel.archives-ouvertes.fr/tel-00522278/en/.
Abstract:
La présente thèse s'intéresse à l'utilisation de méta-données textuelles pour l'analyse d'image. Nous cherchons à utiliser ces informations additionelles comme supervision faible pour l'apprentissage de modèles de reconnaissance visuelle. Nous avons observé un récent et grandissant intérêt pour les méthodes capables d'exploiter ce type de données car celles-ci peuvent potentiellement supprimer le besoin d'annotations manuelles, qui sont coûteuses en temps et en ressources. Nous concentrons nos efforts sur deux types de données visuelles associées à des informations textuelles. Tout d'abord, nous utilisons des images de dépêches qui sont accompagnées de légendes descriptives pour s'attaquer à plusieurs problèmes liés à la reconnaissance de visages. Parmi ces problèmes, la vérification de visages est la tâche consistant à décider si deux images représentent la même personne, et le nommage de visages cherche à associer les visages d'une base de données à leur noms corrects. Ensuite, nous explorons des modèles pour prédire automatiquement les labels pertinents pour des images, un problème connu sous le nom d'annotation automatique d'image. Ces modèles peuvent aussi être utilisés pour effectuer des recherches d'images à partir de mots-clés. Nous étudions enfin un scénario d'apprentissage multimodal semi-supervisé pour la catégorisation d'image. Dans ce cadre de travail, les labels sont supposés présents pour les données d'apprentissage, qu'elles soient manuellement annotées ou non, et absentes des données de test. Nos travaux se basent sur l'observation que la plupart de ces problèmes peuvent être résolus si des mesures de similarité parfaitement adaptées sont utilisées. Nous proposons donc de nouvelles approches qui combinent apprentissage de distance, modèles par plus proches voisins et méthodes par graphes pour apprendre, à partir de données visuelles et textuelles, des similarités visuelles spécifiques à chaque problème. Dans le cas des visages, nos similarités se concentrent sur l'identité des individus tandis que, pour les images, elles concernent des concepts sémantiques plus généraux. Expérimentalement, nos approches obtiennent des performances à l'état de l'art sur plusieurs bases de données complexes. Pour les deux types de données considérés, nous montrons clairement que l'apprentissage bénéficie de l'information textuelle supplémentaire résultant en l'amélioration de la performance des systèmes de reconnaissance visuelle.
8
Ghadie, Mohamed A. "Analysis and Reconstruction of the Hematopoietic Stem Cell Differentiation Tree: A Linear Programming Approach for Gene Selection." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32048.
Abstract:
Stem cells differentiate through an organized hierarchy of intermediate cell types to terminally differentiated cell types. This process is largely guided by master transcriptional regulators, but it also depends on the expression of many other types of genes. The discrete cell types in the differentiation hierarchy are often identified based on the expression or non-expression of certain marker genes. Historically, these have often been various cell-surface proteins, which are fairly easy to assay biochemically but are not necessarily causative of the cell type, in the sense of being master transcriptional regulators. This raises important questions about how gene expression across the whole genome controls or reflects cell state, and in particular, differentiation hierarchies. Traditional approaches to understanding gene expression patterns across multiple conditions, such as principal components analysis or K-means clustering, can group cell types based on gene expression, but they do so without knowledge of the differentiation hierarchy. Hierarchical clustering and maximization of parsimony can organize the cell types into a tree, but in general this tree is different from the differentiation hierarchy. Using hematopoietic differentiation as an example, we demonstrate how many genes other than marker genes are able to discriminate between different branches of the differentiation tree by proposing two models for detecting genes that are up-regulated or down-regulated in distinct lineages. We then propose a novel approach to solving the following problem: Given the differentiation hierarchy and gene expression data at each node, construct a weighted Euclidean distance metric such that the minimum spanning tree with respect to that metric is precisely the given differentiation hierarchy. We provide a set of linear constraints that are provably sufficient for the desired construction and a linear programming framework to identify sparse sets of weights, effectively identifying genes that are most relevant for discriminating different parts of the tree. We apply our method to microarray gene expression data describing 38 cell types in the hematopoiesis hierarchy, constructing a sparse weighted Euclidean metric that uses just 175 genes. These 175 genes are different than the marker genes that were used to identify the 38 cell types, hence offering a novel alternative way of discriminating different branches of the tree. A DAVID functional annotation analysis shows that the 175 genes reflect major processes and pathways active in different parts of the tree. However, we find that there are many alternative sets of weights that satisfy the linear constraints. Thus, in the style of random-forest training, we also construct metrics based on random subsets of the genes and compare them to the metric of 175 genes. Our results show that the 175 genes frequently appear in the random metrics, implicating their significance from an empirical point of view as well. Finally, we show how our linear programming method is able to identify columns that were selected to build minimum spanning trees on the nodes of random variable-size matrices.
9
Chen, Yen-Ting, and 陳彥廷. "Dense Correspondence Annotation of Video Data Using Non-Rigid Registration with Salient Feature Correspondence Constraints." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/68845600289225045103.
Abstract:
碩士國立臺灣大學
資訊工程學研究所
103
There are a few existing annotation systems that aim to provide a platform for video annotation. Most of them focus on activity annotation while others concentrate on labeling individual objects. However, the latters focus on only labeling objects with bounding boxes or only using interpolation techniques to help user labeling. Moreover, only one of them try to find the dense correspondence inside the object contour. Issues of dense correspondences annotation across video frames are not well addressed yet. Inspired by this, a video annotation system that focuses on dense correspondences annotation inside the object contour is proposed in this work. In addition, since labeling detail object contour and dense correspondences across a whole video is a daunting task, we also minimize user''s effort by applying an interactive segmentation and tracking algorithm that utilizes information from optical flow and edges that helps the user easier to observe the salient feature correspondences between two video frames. Edges could help the user to find out the detail contour or local patterns of the object. The user is required to check and modify the salient feature correspondences obtained by the algorithm. Dense correspondences in the textureless region are extracted by a non-rigid registration algorithm from the salient feature correspondences verified by the user. The user only needs to label the first frame of the video and correct some minor errors in the subsequent frames for the whole video annotation. The result shows that the proposed framework is more suitable to label non-rigid objects.
Books on the topic "Constraints annotation":
1
Williams, Dana A. Contemporary African American Female Playwrights. Greenwood Publishing Group, Inc., 1998. http://dx.doi.org/10.5040/9798400631115.
Abstract:
Lorraine Hansberry's A Raisin in the Sun (1959) was a major dramatic success and brought to the world's attention the potential talent of African American women playwrights. But in spite of Hansberry's landmark contribution, both the theater and the literary world have often failed to include contemporary African American female playwrights within the circle of production, publication, and criticism. In African American drama anthologies, female playwrights are seldom given the degree of attention that is accorded their male counterparts. And because of space constraints, anthologies of works by women playwrights are forced to exclude numerous female dramatists, including African Americans. Meanwhile, some scholars have argued that the works of African American female playwrights are seldom produced in the mainstream theater because these plays frequently challenge the views of white America. But as A Raisin in the Sun demonstrates, plays by African American women dramatists can have a powerful message and are worthy of attention. A comprehensive research tool, this annotated bibliography sheds light on the often neglected works of contemporary African American female playwrights. Included within its scope are those dramatists who have had at least one work published since 1959, the year of Hansberry's monumental achievement. The first section provides a listing of anthologies that include one or more plays written by an African American female dramatist. The second gives entries for reference works and for scholarly and critical studies of the dramatists and their plays. The third presents a listing of published plays by individual dramatists, along with a summary of each drama; the works of each playwright that are related to drama; and secondary sources that treat the dramatists and their plays. Entries are accompanied by concise but informative annotations, and the volume closes with a list of periodicals that frequently publish criticism of African American female playwrights, a section of brief biographical sketches of the dramatists, and extensive indexes.
Book chapters on the topic "Constraints annotation":
1
Kasahara, Hidekazu, Mikihiko Mori, Masayuki Mukunoki, and Michihiko Minoh. "Transportation Mode Annotation of Tourist GPS Trajectories Under Environmental Constraints." In Information and Communication Technologies in Tourism 2015, 523–35. Cham: Springer International Publishing, 2014. http://dx.doi.org/10.1007/978-3-319-14343-9_38.
2
Cao, Yu, Lili Ju, and Song Wang. "Grain Segmentation of 3D Superalloy Images Using Multichannel EWCVT under Human Annotation Constraints." In Computer Vision – ECCV 2012, 244–57. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-33712-3_18.
3
Rudova, Hana. "Constraints with Variables’ Annotations and Constraint Hierarchies." In SOFSEM’ 98: Theory and Practice of Informatics, 409–18. Berlin, Heidelberg: Springer Berlin Heidelberg, 1998. http://dx.doi.org/10.1007/3-540-49477-4_33.
4
Wingen, Isabel, and Philipp Körner. "Effectiveness of Annotation-Based Static Type Inference." In Functional and Constraint Logic Programming, 74–93. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-75333-7_5.
5
Sassen, Claudia, and Peter Kühnlein. "Annotating Structural Constraints in Discourse Corpora." In Text, Speech and Dialogue, 435–42. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11551874_56.
6
Han, Jiajie, Jiani Hu, and Weihong Deng. "Constrained Spectral Clustering on Face Annotation System." In Communications in Computer and Information Science, 3–12. Singapore: Springer Singapore, 2016. http://dx.doi.org/10.1007/978-981-10-3002-4_1.
7
Dong, Yongquan, Qingzhong Li, Yongqing Zheng, Xiaoyang Xu, and Yongxin Zhang. "Semantic Annotation of Web Objects Using Constrained Conditional Random Fields." In Web-Age Information Management, 28–39. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-14246-8_6.
8
Hughes, Jack, and Dominic Orchard. "Program Synthesis from Graded Types." In Programming Languages and Systems, 83–112. Cham: Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-57262-3_4.
Abstract:
AbstractGraded type systems are a class of type system for fine-grained quantitative reasoning about data-flow in programs. Through the use of resource annotations (or grades), a programmer can express various program properties at the type level, reducing the number of typeable programs. These additional constraints on types lend themselves naturally to type-directed program synthesis, where this information can be exploited to constrain the search space of programs. We present a synthesis algorithm for a graded type system, where grades form an arbitrary pre-ordered semiring. Harnessing this grade information in synthesis is non-trivial, and we explore some of the issues involved in designing and implementing a resource-aware program synthesis tool. In our evaluation we show that by harnessing grades in synthesis, the majority of our benchmark programs (many of which involve recursive functions over recursive ADTs) require less exploration of the synthesis search space than a purely type-driven approach and with fewer needed input-output examples. This type-and-graded-directed approach is demonstrated for the research language Granule but we also adapt it for synthesising Haskell programs that use GHC’s linear types extension.
9
Xiaoguang, Rui, Yuan Pingbo, and Yu Nenghai. "Image Annotations Based on Semi-supervised Clustering with Semantic Soft Constraints." In Advances in Multimedia Information Processing - PCM 2006, 624–32. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006. http://dx.doi.org/10.1007/11922162_72.
10
Detyniecki, Marcin. "Browsing a Video with Simple Constrained Queries over Fuzzy Annotations." In Flexible Query Answering Systems, 282–88. Heidelberg: Physica-Verlag HD, 2001. http://dx.doi.org/10.1007/978-3-7908-1834-5_26.
Conference papers on the topic "Constraints annotation":
1
Chen, Zhijun, Huimin Wang, Hailong Sun, Pengpeng Chen, Tao Han, Xudong Liu, and Jie Yang. "Structured Probabilistic End-to-End Learning from Crowds." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/210.
Abstract:
End-to-end learning from crowds has recently been introduced as an EM-free approach to training deep neural networks directly from noisy crowdsourced annotations. It models the relationship between true labels and annotations with a specific type of neural layer, termed as the crowd layer, which can be trained using pure backpropagation. Parameters of the crowd layer, however, can hardly be interpreted as annotator reliability, as compared with the more principled probabilistic approach. The lack of probabilistic interpretation further prevents extensions of the approach to account for important factors of annotation processes, e.g., instance difficulty. This paper presents SpeeLFC, a structured probabilistic model that incorporates the constraints of probability axioms for parameters of the crowd layer, which allows to explicitly model annotator reliability while benefiting from the end-to-end training of neural networks. Moreover, we propose SpeeLFC-D, which further takes into account instance difficulty. Extensive validation on real-world datasets shows that our methods improve the state-of-the-art.
2
Yuan, Jinhui, Jianmin Li, and Bo Zhang. "Exploiting spatial context constraints for automatic image region annotation." In the 15th international conference. New York, New York, USA: ACM Press, 2007. http://dx.doi.org/10.1145/1291233.1291379.
3
C. Ribeiro, Fabiola Goncalves, Achim Rettberg, Carlos E. Pereira, Charles Steinmetz, and Michel S. Soares. "Non-functional Constraints Annotation to Real-Time Embedded System Design." In 2018 VIII Brazilian Symposium on Computing Systems Engineering (SBESC). IEEE, 2018. http://dx.doi.org/10.1109/sbesc.2018.00041.
4
Guo, Kunpeng, Dennis Diefenbach, Antoine Gourru, and Christophe Gravier. "Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints." In 2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2023. http://dx.doi.org/10.1109/ictai59109.2023.00032.
5
Pardo, Alejandro, Mengmeng Xu, Ali Thabet, Pablo Arbelaez, and Bernard Ghanem. "BAOD: Budget-Aware Object Detection." In LatinX in AI at Computer Vision and Pattern Recognition Conference 2021. Journal of LatinX in AI Research, 2021. http://dx.doi.org/10.52591/lxai202106254.
Abstract:
We study the problem of object detection from a novel perspective in which annotation budget constraints are taken into consideration, appropriately coined Budget Aware Object Detection (BAOD). When provided with a fixed budget, we propose a strategy for building a diverse and informative dataset that can be used to optimally train a robust detector. We investigate both optimization and learning-based methods to sample which images to annotate and what type of annotation (strongly or weakly supervised) to annotate them with. We adopt a hybrid supervised learning framework to train the object detector from both these types of annotation. We conduct a comprehensive empirical study showing that a handcrafted optimization method outperforms other selection techniques including random sampling, uncertainty sampling and active learning. By combining an optimal image/annotation selection scheme with hybrid supervised learning to solve the BAOD problem, we show that one can achieve the performance of a strongly supervised detector on PASCAL-VOC 2007 while saving 12.8% of its original annotation budget. Furthermore, when 100% of the budget is used, it surpasses this performance by 2.0 mAP percentage points.
6
Trandabat, Diana. "SEMANTIC ROLE ANNOTATION FOR ELEARNING." In eLSE 2017. Carol I National Defence University Publishing House, 2017. http://dx.doi.org/10.12753/2066-026x-17-179.
Abstract:
The analysis of semantic roles reveals the hidden structure of a sentence and contributes to the construction of meaning, identifying specific roles that entities play in various contexts and actors involved in an event. The semantic role expresses the correlation between a predicate and its arguments. This paper describes a preliminary study about the impact semantic roles could have in eLearning contexts. The goal of our application is to identify, from a collection of learning materials, all contexts referring to a specific entity, in order to analyse relations between the entity and words with which it frequently co-occurs. Thus, through semantic role analysis, we intend to determine temporal, spatial or modal constraints which determine or restrict a concept. More concretely, the system we propose starts from an input concept, searches learning materials for that particular concept, selects the snippets that contains it, and applies semantic role labelling. At a further step, we extract semantic relations between the entity and neighbouring words, resulting in a list of binary relations. Finally, the program uses WordNet hypernyms trying to generalize over all extracted snippets. Thus, the program may facilitate the understanding of the concept through its neighbours, by creating a map of structured data related to a target concept, where each related entity is marked with its corresponding role (which can be of type Agent, Patient, Effect, Location, Cause, Time, etc.).
7
Mullick, Ankan. "Exploring Multilingual Intent Dynamics and Applications." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California: International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/818.
Abstract:
Multilingual Intent Detection and explore its different characteristics are major field of study for last few years. But, detection of intention dynamics from text or voice, especially in the Indian multilingual contexts, is a challenging task. So, my first research question is on intent detection and then I work on the application in Indian Multilingual Healthcare scenario. Speech dialogue systems are designed by a pre-defined set of intents to perform user specified tasks. Newer intentions may surface over time that call for retraining. However, the newer intents may not be explicitly announced and need to be inferred dynamically. Hence, here are two crucial jobs: (a) recognizing newly emergent intents; and (b) annotating the data of the new intents in order to effectively retrain the underlying classifier. The tasks become specially challenging when a large number of new intents emerge simultaneously and there is a limited budget of manual annotation. We develop MNID (Multiple Novel Intent Detection), a cluster based framework that can identify multiple novel intents while optimized human annotation cost. Empirical findings on numerous benchmark datasets (of varying sizes) show that MNID surpasses the baseline approaches in terms of accuracy and F1-score by wisely allocating the budget for annotation. We apply intent detection approach on different domains in Indian multilingual scenarios - healthcare, finance etc. The creation of advanced NLU healthcare systems is threatened by the lack of data and technology constraints for resource-poor languages in developing nations like India. We evaluate the current state of several cutting-edge language models used in the healthcare with the goal of detecting query intents and corresponding entities. We conduct comprehensive trials on a number of models different realistic contexts, and we investigate the practical relevance depending on budget and the availability of data on English.
8
Jin, Wanjun, Rui Shi, and Tat-Seng Chua. "A semi-na�ve Bayesian method incorporating clustering with pair-wise constraints for auto image annotation." In the 12th annual ACM international conference. New York, New York, USA: ACM Press, 2004. http://dx.doi.org/10.1145/1027527.1027605.
9
Tejero, Javier Gamazo, Martin S. Zinkernagel, Sebastian Wolf, Raphael Sznitman, and Pablo Márquez Neila. "Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns." In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2023. http://dx.doi.org/10.1109/cvpr52729.2023.01095.
10
Ma, Jiayao, Xinbo Jiang, Songhua Xu, and Xueying Qin. "Hierarchical Temporal Multi-Instance Learning for Video-based Student Learning Engagement Assessment." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/383.
Abstract:
Video-based automatic assessment of a student's learning engagement on the fly can provide immense values for delivering personalized instructional services, a vehicle particularly important for massive online education. To train such an assessor, a major challenge lies in the collection of sufficient labels at the appropriate temporal granularity since a learner's engagement status may continuously change throughout a study session. Supplying labels at either frame or clip level incurs a high annotation cost. To overcome such a challenge, this paper proposes a novel hierarchical multiple instance learning (MIL) solution, which only requires labels anchored on full-length videos to learn to assess student engagement at an arbitrary temporal granularity and for an arbitrary duration in a study session. The hierarchical model mainly comprises a bottom module and a top module, respectively dedicated to learning the latent relationship between a clip and its constituent frames and that between a video and its constituent clips, with the constraints on the training stage that the average engagements of local clips is that of the video label. To verify the effectiveness of our method, we compare the performance of the proposed approach with that of several state-of-the-art peer solutions through extensive experiments.
Reports on the topic "Constraints annotation":
1
Ghanim, Murad, Joe Cicero, Judith K. Brown, and Henryk Czosnek. Dissection of Whitefly-geminivirus Interactions at the Transcriptomic, Proteomic and Cellular Levels. United States Department of Agriculture, February 2010. http://dx.doi.org/10.32747/2010.7592654.bard.
Abstract:
Our project focuses on gene expression and proteomics of the whitefly Bemisia tabaci (Gennadius) species complex in relation to the internal anatomy and localization of expressed genes and virions in the whitefly vector, which poses a major constraint to vegetable and fiber production in Israel and the USA. While many biological parameters are known for begomovirus transmission, nothing is known about vector proteins involved in the specific interactions between begomoviruses and their whitefly vectors. Identifying such proteins is expected to lead to the design of novel control methods that interfere with whitefly-mediated begomovirus transmission. The project objectives were to: 1) Perform gene expression analyses using microarrays to study the response of whiteflies (B, Q and A biotypes) to the acquisition of begomoviruses (Tomato yellow leaf curl (TYLCV) and Squash leaf curl (SLCV). 2) Construct a whitefly proteome from whole whiteflies and dissected organs after begomovirus acquisition. 3) Validate gene expression by q-RTPCR and sub-cellular localization of candidate ESTs identified in microarray and proteomic analyses. 4) Verify functionality of candidate ESTs using an RNAi approach, and to link these datasets to overall functional whitefly anatomical studies. During the first and second years biological experiments with TYLCV and SLCV acquisition and transmission were completed to verify the suitable parameters for sample collection for microarray experiments. The parameters were generally found to be similar to previously published results by our groups and others. Samples from whole whiteflies and midguts of the B, A and Q biotypes that acquired TYLCV and SLCV were collected in both the US and Israel and hybridized to B. tabaci microarray. The data we analyzed, candidate genes that respond to both viruses in the three tested biotypes were identified and their expression that included quantitative real-time PCR and co-localization was verified for HSP70 by the Israeli group. In addition, experiments were undertaken to employ in situ hybridization to localize several candidate genes (in progress) using an oligonucleotide probe to the primary endosymbiont as a positive control. A proteome and corresponding transcriptome to enable more effective protein identification of adult whiteflies was constructed by the US group. Further validation of the transmission route of begomoviruses, mainly SLCV and the involvement of the digestive and salivary systems was investigated (Cicero and Brown). Due to time and budget constraints the RNAi-mediated silencing objective to verify gene function was not accomplished as anticipated. HSP70, a strong candidate protein that showed over-expression after TYLCV and SLCV acquisition and retention by B. tabaci, and co-localization with TYLCV in the midgut, was further studies. Besides this protein, our joint research resulted in the identification of many intriguing candidate genes and proteins that will be followed up by additional experiments during our future research. To identify these proteins it was necessary to increase the number and breadth of whitefly ESTs substantially and so whitefly cDNAs from various libraries made during the project were sequenced (Sanger, 454). As a result, the proteome annotation (ID) was far more successful than in the initial attempt to identify proteins using Uniprot or translated insect ESTs from public databases. The extent of homology shared by insects in different orders was surprisingly low, underscoring the imperative need for genome and transcriptome sequencing of homopteran insects. Having increased the number of EST from the original usable 5500 generated several years ago to >600,000 (this project+NCBI data mining), we have identified about one fifth of the whitefly proteome using these new resources. Also we have created a database that links all identified whitefly proteins to the PAVEdb-ESTs in the database, resulting in a useful dataset to which additional ESTS will be added. We are optimistic about the prospect of linking the proteome ID results to the transcriptome database to enable our own and other labs the opportunity to functionally annotate not only genes and proteins involved in our area of interest (whitefly mediated transmission) but for the plethora of other functionalities that will emerge from mining and functionally annotating other key genes and gene families in whitefly metabolism, development, among others. This joint grant has resulted in the identification of numerous candidate proteins involved in begomovirus transmission by B. tabaci. A next major step will be to capitalize on validated genes/proteins to develop approaches to interfere with the virus transmission.