TV newscasts report about the latest event-related facts occurring in the world. Relying exclusiv... more TV newscasts report about the latest event-related facts occurring in the world. Relying exclusively on them is, however, insufficient to fully grasp the context of the story being reported. In this paper, we propose an approach that retrieves and analyzes related documents from the Web to automatically generate semantic annotations that provide viewers and experts comprehensive information about the news. We detect named entities in the retrieved documents that further disclose relevant concepts that were not explicitly mentioned in the original newscast. A ranking algorithm based on entity frequency, popularity peak analysis, and domain experts' rules sorts those annotations to generate what we call Semantic Snapshot of a Newscast (NSS). We benchmark this method against a gold standard generated by domain experts and assessed via a user survey over five BBC newscasts. Results of the experiments show the robustness of our approach holding an Average Normalized Discounted Cumula...
MPEG-7 can be used to create complex and comprehensive metadata descriptions of multimedia conten... more MPEG-7 can be used to create complex and comprehensive metadata descriptions of multimedia content. Since MPEG-7 is defined in terms of an XML schema, the semantics of its elements has no formal grounding. In addition, certain features can be described in multiple ways. MPEG-7 profiles are subsets of the standard that apply to specific application areas and that aim to
This paper describes the VAMP web application for the validation of MPEG-7 descriptions with resp... more This paper describes the VAMP web application for the validation of MPEG-7 descriptions with respect to semantic constraints dened in a prole. The
Entities play a key role in knowledge bases in general and in the Web of Data in particular. Enti... more Entities play a key role in knowledge bases in general and in the Web of Data in particular. Entities are generally described with a lot of properties, this is the case for DBpedia. It is, however, difficult to assess which ones are more "important" than others for particular tasks such as visualizing the key facts of an entity or filtering out the ones which will yield better instance matching. In this paper, we perform a reverse engineering of the Google Knowledge graph panel to find out what are the most "important" properties for an entity according to Google. We compare these results with a survey we conducted on 152 users. We finally show how we can represent and explicit this knowledge using the Fresnel vocabulary.
This demo enables the automatic creation of semantically annotated YouTube media fragments. A vid... more This demo enables the automatic creation of semantically annotated YouTube media fragments. A video is first ingested in the Synote system and a new method enables to retrieve its associated sub-titles or closed captions. Next, NERD is used to extract named entities from the transcripts which are then temporally aligned with the video. The entities are disambiguated in the LOD cloud and a user interface enables to browse through the entities detected in a video or get more in-formation. We evaluated our application with 60 videos from 3 YouTube channels.
TV newscasts report about the latest event-related facts occurring in the world. Relying exclusiv... more TV newscasts report about the latest event-related facts occurring in the world. Relying exclusively on them is, however, insufficient to fully grasp the context of the story being reported. In this paper, we propose an approach that retrieves and analyzes related documents from the Web to automatically generate semantic annotations that provide viewers and experts comprehensive information about the news. We detect named entities in the retrieved documents that further disclose relevant concepts that were not explicitly mentioned in the original newscast. A ranking algorithm based on entity frequency, popularity peak analysis, and domain experts' rules sorts those annotations to generate what we call Semantic Snapshot of a Newscast (NSS). We benchmark this method against a gold standard generated by domain experts and assessed via a user survey over five BBC newscasts. Results of the experiments show the robustness of our approach holding an Average Normalized Discounted Cumula...
MPEG-7 can be used to create complex and comprehensive metadata descriptions of multimedia conten... more MPEG-7 can be used to create complex and comprehensive metadata descriptions of multimedia content. Since MPEG-7 is defined in terms of an XML schema, the semantics of its elements has no formal grounding. In addition, certain features can be described in multiple ways. MPEG-7 profiles are subsets of the standard that apply to specific application areas and that aim to
This paper describes the VAMP web application for the validation of MPEG-7 descriptions with resp... more This paper describes the VAMP web application for the validation of MPEG-7 descriptions with respect to semantic constraints dened in a prole. The
Entities play a key role in knowledge bases in general and in the Web of Data in particular. Enti... more Entities play a key role in knowledge bases in general and in the Web of Data in particular. Entities are generally described with a lot of properties, this is the case for DBpedia. It is, however, difficult to assess which ones are more "important" than others for particular tasks such as visualizing the key facts of an entity or filtering out the ones which will yield better instance matching. In this paper, we perform a reverse engineering of the Google Knowledge graph panel to find out what are the most "important" properties for an entity according to Google. We compare these results with a survey we conducted on 152 users. We finally show how we can represent and explicit this knowledge using the Fresnel vocabulary.
This demo enables the automatic creation of semantically annotated YouTube media fragments. A vid... more This demo enables the automatic creation of semantically annotated YouTube media fragments. A video is first ingested in the Synote system and a new method enables to retrieve its associated sub-titles or closed captions. Next, NERD is used to extract named entities from the transcripts which are then temporally aligned with the video. The entities are disambiguated in the LOD cloud and a user interface enables to browse through the entities detected in a video or get more in-formation. We evaluated our application with 60 videos from 3 YouTube channels.
Multimedia Semantics: Metadata, Analysis and Interaction, 2011
This chapter presents the Core Ontology for Multimedia (COMM), which provides a formal semantics ... more This chapter presents the Core Ontology for Multimedia (COMM), which provides a formal semantics for multimedia annotations to enable interoperability of multimedia metadata among media tools. COMM maps the core functionalities of the MPEG-7 standard to a formal ontology, following an ontology design approach that utilizes the foundational Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE) ontology to safeguard conceptual clarity and soundness as well as extensibility towards new annotation requirements. The chapter analyzes the requirements underlying the semantic representation of media objects, explains why the requirements are not fulfilled by most semantic multimedia ontologies and presents solutions as implemented by COMM.
We present results of collaborative work bringing together semantic technologies, machine learnin... more We present results of collaborative work bringing together semantic technologies, machine learning and cultural heritage to enable advanced search and visualization of textual descriptions of museum artifacts related to silk fabrics. Proposed is a multilingual txt analysis approach where the developed domain-specific multilingual thesaurus and domain-specific ontology are utilized in data representation and analysis. In addition, a general multilingual semantic annotation tool Wikifier is applied on thesaurus definitions and descriptions of silk-related museum artefacts. The validation on real-world data of several museums confirms suitability of the developed thesaurus and the ontology.
Uploads
Papers by Raphael Troncy