• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.18 no.2
• /
• pp.49-63
• /
• 2008

RDF is the base ontology model which is used in Semantic Web defined by W3C. OWL expands the RDF base model by providing various vocabularies for defining much more ontology relationships. Recently Jain and Farkas have suggested an RDF access control model based on RDF triple. Their research point is to introduce an authorization conflict problem by RDF inference which must be considered in RDF ontology data. Due to the problem, we cannot adopt XML access control model for RDF, although RDF is represented by XML. However, Jain and Farkas did not define the authorization propagation over the RDF upper/lower ontology concepts when an RDF authorization is specified. The reason why the authorization specification should be defined clearly is that finally, the authorizatin conflict is the problem between the authorization propagation in specifying an authorization and the authorization propagation in inferencing authorizations. In this article, first we define an RDF access authorization specification based on RDF triple in detail. Next, based on the definition, we analyze the authoriztion conflict problem by RDF inference in detail. Next, we briefly introduce a method which can quickly find an authorization conflict by using graph labeling techniques. This method is especially related with the subsumption relationship based inference. Finally, we present a comparison analysis with Jain and Farkas' study, and some experimental results showing the efficiency of the suggested conflict detection method.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.