際際滷shows by User: shekarpour / http://www.slideshare.net/images/logo.gif 際際滷shows by User: shekarpour / Wed, 03 Apr 2019 16:24:51 GMT 際際滷Share feed for 際際滷shows by User: shekarpour Metrics for Evaluating Quality of Embeddings for Ontological Concepts /slideshow/metrics-for-evaluating-quality-of-embeddings-for-ontological-concepts/139431216 aaai-make-190403162451
Although there is an emerging trend towards generating embeddings for primarily unstructured data and, recently, for structured data, no systematic suite for measuring the quality of embeddings has been proposed yet. This deficiency is further sensed with respect to embeddings generated for structured data because there are no concrete evaluation metrics measuring the quality of the encoded structure as well as semantic patterns in the embedding space. In this paper, we introduce a framework containing three distinct tasks concerned with the individual aspects of ontological concepts: (i) the categorization aspect, (ii) the hierarchical aspect, and (iii) the relational aspect. Then, in the scope of each task, a number of intrinsic metrics are proposed for evaluating the quality of the embeddings. Furthermore, w.r.t. this framework, multiple experimental studies were run to compare the quality of the available embedding models. Employing this framework in future research can reduce misjudgment and provide greater insight about quality comparisons of embeddings for ontological concepts. We positioned our sampled data and code at https://github.com/alshargi/Concept2vec under GNU General Public License v3.0.]]>
Although there is an emerging trend towards generating embeddings for primarily unstructured data and, recently, for structured data, no systematic suite for measuring the quality of embeddings has been proposed yet. This deficiency is further sensed with respect to embeddings generated for structured data because there are no concrete evaluation metrics measuring the quality of the encoded structure as well as semantic patterns in the embedding space. In this paper, we introduce a framework containing three distinct tasks concerned with the individual aspects of ontological concepts: (i) the categorization aspect, (ii) the hierarchical aspect, and (iii) the relational aspect. Then, in the scope of each task, a number of intrinsic metrics are proposed for evaluating the quality of the embeddings. Furthermore, w.r.t. this framework, multiple experimental studies were run to compare the quality of the available embedding models. Employing this framework in future research can reduce misjudgment and provide greater insight about quality comparisons of embeddings for ontological concepts. We positioned our sampled data and code at https://github.com/alshargi/Concept2vec under GNU General Public License v3.0.]]> Wed, 03 Apr 2019 16:24:51 GMT /slideshow/metrics-for-evaluating-quality-of-embeddings-for-ontological-concepts/139431216 shekarpour@slideshare.net(shekarpour) Metrics for Evaluating Quality of Embeddings for Ontological Concepts shekarpour Although there is an emerging trend towards generating embeddings for primarily unstructured data and, recently, for structured data, no systematic suite for measuring the quality of embeddings has been proposed yet. This deficiency is further sensed with respect to embeddings generated for structured data because there are no concrete evaluation metrics measuring the quality of the encoded structure as well as semantic patterns in the embedding space. In this paper, we introduce a framework containing three distinct tasks concerned with the individual aspects of ontological concepts: (i) the categorization aspect, (ii) the hierarchical aspect, and (iii) the relational aspect. Then, in the scope of each task, a number of intrinsic metrics are proposed for evaluating the quality of the embeddings. Furthermore, w.r.t. this framework, multiple experimental studies were run to compare the quality of the available embedding models. Employing this framework in future research can reduce misjudgment and provide greater insight about quality comparisons of embeddings for ontological concepts. We positioned our sampled data and code at https://github.com/alshargi/Concept2vec under GNU General Public License v3.0. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aaai-make-190403162451-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Although there is an emerging trend towards generating embeddings for primarily unstructured data and, recently, for structured data, no systematic suite for measuring the quality of embeddings has been proposed yet. This deficiency is further sensed with respect to embeddings generated for structured data because there are no concrete evaluation metrics measuring the quality of the encoded structure as well as semantic patterns in the embedding space. In this paper, we introduce a framework containing three distinct tasks concerned with the individual aspects of ontological concepts: (i) the categorization aspect, (ii) the hierarchical aspect, and (iii) the relational aspect. Then, in the scope of each task, a number of intrinsic metrics are proposed for evaluating the quality of the embeddings. Furthermore, w.r.t. this framework, multiple experimental studies were run to compare the quality of the available embedding models. Employing this framework in future research can reduce misjudgment and provide greater insight about quality comparisons of embeddings for ontological concepts. We positioned our sampled data and code at https://github.com/alshargi/Concept2vec under GNU General Public License v3.0.
Metrics for Evaluating Quality of Embeddings for Ontological Concepts from Saeedeh Shekarpour
]]> 761 2 https://cdn.slidesharecdn.com/ss_thumbnails/aaai-make-190403162451-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 CEVO: Comprehensive EVent Ontology Enhancing Cognitive Annotation on Relations /slideshow/cevo-comprehensive-event-ontology-enhancing-cognitive-annotation-on-relations/130283497 cevo2-190202133718
While the general analysis of named entities has received substantial research attention on unstructured as well as structured data, the analysis of relations among named entities has received limited focus. In fact, a review of the literature revealed a deficiency in research on the abstract conceptualization required to organize relations. We believe that such an abstract conceptualization can benefit various communities and applications such as natural language processing, information extraction, machine learning, and ontology engineering. In this paper, we present Comprehensive EVent Ontology (CEVO), built on Levin's conceptual hierarchy of English verbs that categorizes verbs with shared meaning, and syntactic behavior. We present the fundamental concepts and requirements for this ontology. Furthermore, we present three use cases employing the CEVO ontology on annotation tasks: (i) annotating relations in plain text, (ii) annotating ontological properties, and (iii) linking textual relations to ontological properties. These use-cases demonstrate the benefits of using CEVO for annotation: (i) annotating English verbs from an abstract conceptualization, (ii) playing the role of an upper ontology for organizing ontological properties, and (iii) facilitating the annotation of text relations using any underlying vocabulary. This resource is available at https://shekarpour.github.io/cevo.io/ using https://w3id.org/cevo namespace.]]>
While the general analysis of named entities has received substantial research attention on unstructured as well as structured data, the analysis of relations among named entities has received limited focus. In fact, a review of the literature revealed a deficiency in research on the abstract conceptualization required to organize relations. We believe that such an abstract conceptualization can benefit various communities and applications such as natural language processing, information extraction, machine learning, and ontology engineering. In this paper, we present Comprehensive EVent Ontology (CEVO), built on Levin's conceptual hierarchy of English verbs that categorizes verbs with shared meaning, and syntactic behavior. We present the fundamental concepts and requirements for this ontology. Furthermore, we present three use cases employing the CEVO ontology on annotation tasks: (i) annotating relations in plain text, (ii) annotating ontological properties, and (iii) linking textual relations to ontological properties. These use-cases demonstrate the benefits of using CEVO for annotation: (i) annotating English verbs from an abstract conceptualization, (ii) playing the role of an upper ontology for organizing ontological properties, and (iii) facilitating the annotation of text relations using any underlying vocabulary. This resource is available at https://shekarpour.github.io/cevo.io/ using https://w3id.org/cevo namespace.]]> Sat, 02 Feb 2019 13:37:18 GMT /slideshow/cevo-comprehensive-event-ontology-enhancing-cognitive-annotation-on-relations/130283497 shekarpour@slideshare.net(shekarpour) CEVO: Comprehensive EVent Ontology Enhancing Cognitive Annotation on Relations shekarpour While the general analysis of named entities has received substantial research attention on unstructured as well as structured data, the analysis of relations among named entities has received limited focus. In fact, a review of the literature revealed a deficiency in research on the abstract conceptualization required to organize relations. We believe that such an abstract conceptualization can benefit various communities and applications such as natural language processing, information extraction, machine learning, and ontology engineering. In this paper, we present Comprehensive EVent Ontology (CEVO), built on Levin's conceptual hierarchy of English verbs that categorizes verbs with shared meaning, and syntactic behavior. We present the fundamental concepts and requirements for this ontology. Furthermore, we present three use cases employing the CEVO ontology on annotation tasks: (i) annotating relations in plain text, (ii) annotating ontological properties, and (iii) linking textual relations to ontological properties. These use-cases demonstrate the benefits of using CEVO for annotation: (i) annotating English verbs from an abstract conceptualization, (ii) playing the role of an upper ontology for organizing ontological properties, and (iii) facilitating the annotation of text relations using any underlying vocabulary. This resource is available at https://shekarpour.github.io/cevo.io/ using https://w3id.org/cevo namespace. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cevo2-190202133718-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> While the general analysis of named entities has received substantial research attention on unstructured as well as structured data, the analysis of relations among named entities has received limited focus. In fact, a review of the literature revealed a deficiency in research on the abstract conceptualization required to organize relations. We believe that such an abstract conceptualization can benefit various communities and applications such as natural language processing, information extraction, machine learning, and ontology engineering. In this paper, we present Comprehensive EVent Ontology (CEVO), built on Levin&#39;s conceptual hierarchy of English verbs that categorizes verbs with shared meaning, and syntactic behavior. We present the fundamental concepts and requirements for this ontology. Furthermore, we present three use cases employing the CEVO ontology on annotation tasks: (i) annotating relations in plain text, (ii) annotating ontological properties, and (iii) linking textual relations to ontological properties. These use-cases demonstrate the benefits of using CEVO for annotation: (i) annotating English verbs from an abstract conceptualization, (ii) playing the role of an upper ontology for organizing ontological properties, and (iii) facilitating the annotation of text relations using any underlying vocabulary. This resource is available at https://shekarpour.github.io/cevo.io/ using https://w3id.org/cevo namespace.
CEVO: Comprehensive EVent Ontology Enhancing Cognitive Annotation on Relations from Saeedeh Shekarpour
]]> 114 3 https://cdn.slidesharecdn.com/ss_thumbnails/cevo2-190202133718-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 A quality type aware annotated corpus and lexicon for harassment research /slideshow/a-quality-type-aware-annotated-corpus-and-lexicon-for-harassment-research/99168332 aqualitytype-awareannotatedcorpusandlexiconforharassmentresearch-180528072046
Presented in Web Science 2018 conference, Amsterdam, May 2018]]>
Presented in Web Science 2018 conference, Amsterdam, May 2018]]> Mon, 28 May 2018 07:20:46 GMT /slideshow/a-quality-type-aware-annotated-corpus-and-lexicon-for-harassment-research/99168332 shekarpour@slideshare.net(shekarpour) A quality type aware annotated corpus and lexicon for harassment research shekarpour Presented in Web Science 2018 conference, Amsterdam, May 2018 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aqualitytype-awareannotatedcorpusandlexiconforharassmentresearch-180528072046-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Presented in Web Science 2018 conference, Amsterdam, May 2018
A quality type aware annotated corpus and lexicon for harassment research from Saeedeh Shekarpour
]]> 230 4 https://cdn.slidesharecdn.com/ss_thumbnails/aqualitytype-awareannotatedcorpusandlexiconforharassmentresearch-180528072046-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Windowing of attention /slideshow/windowing-of-attention/63144755 windowingofattention-160616161021
Towards a cognitive semantics Part 3 Leonard Talmy Presenter: Saeedeh Shekarpour ]]>
Towards a cognitive semantics Part 3 Leonard Talmy Presenter: Saeedeh Shekarpour ]]> Thu, 16 Jun 2016 16:10:20 GMT /slideshow/windowing-of-attention/63144755 shekarpour@slideshare.net(shekarpour) Windowing of attention shekarpour Towards a cognitive semantics Part 3 Leonard Talmy Presenter: Saeedeh Shekarpour <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/windowingofattention-160616161021-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Towards a cognitive semantics Part 3 Leonard Talmy Presenter: Saeedeh Shekarpour
Windowing of attention from Saeedeh Shekarpour
]]> 1024 5 https://cdn.slidesharecdn.com/ss_thumbnails/windowingofattention-160616161021-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Tutorial on Question Answering Systems /slideshow/tutorial-on-question-answering-systems/52269793 summerschoolpresentation-150831220329-lva1-app6891
Tutorial on Question Answering Systems in Web Intelligence Summer School 2015]]>
Tutorial on Question Answering Systems in Web Intelligence Summer School 2015]]> Mon, 31 Aug 2015 22:03:29 GMT /slideshow/tutorial-on-question-answering-systems/52269793 shekarpour@slideshare.net(shekarpour) Tutorial on Question Answering Systems shekarpour Tutorial on Question Answering Systems in Web Intelligence Summer School 2015 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/summerschoolpresentation-150831220329-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Tutorial on Question Answering Systems in Web Intelligence Summer School 2015
Tutorial on Question Answering Systems from Saeedeh Shekarpour
]]> 11818 37 https://cdn.slidesharecdn.com/ss_thumbnails/summerschoolpresentation-150831220329-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Semantic Interpretation of User Query for Question Answering on Interlinked Data /slideshow/defense-43354645/43354645 defensepresentatio-150109065554-conversion-gate02
My PhD defense slides at the Bonn university Query Segmentation, Resource disambiguation, Federated Query Construction, Query Expansion]]>
My PhD defense slides at the Bonn university Query Segmentation, Resource disambiguation, Federated Query Construction, Query Expansion]]> Fri, 09 Jan 2015 06:55:54 GMT /slideshow/defense-43354645/43354645 shekarpour@slideshare.net(shekarpour) Semantic Interpretation of User Query for Question Answering on Interlinked Data shekarpour My PhD defense slides at the Bonn university Query Segmentation, Resource disambiguation, Federated Query Construction, Query Expansion <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/defensepresentatio-150109065554-conversion-gate02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> My PhD defense slides at the Bonn university Query Segmentation, Resource disambiguation, Federated Query Construction, Query Expansion
Semantic Interpretation of User Query for Question Answering on Interlinked Data from Saeedeh Shekarpour
]]> 1398 4 https://cdn.slidesharecdn.com/ss_thumbnails/defensepresentatio-150109065554-conversion-gate02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Sina presentation in IBM /slideshow/sina-presentation-in-ibm/29140620 sina-ibm-131212050740-phpapp02
]]>
]]> Thu, 12 Dec 2013 05:07:40 GMT /slideshow/sina-presentation-in-ibm/29140620 shekarpour@slideshare.net(shekarpour) Sina presentation in IBM shekarpour <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/sina-ibm-131212050740-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Sina presentation in IBM from Saeedeh Shekarpour
]]> 1395 5 https://cdn.slidesharecdn.com/ss_thumbnails/sina-ibm-131212050740-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Wi presentation /slideshow/wi-presentation/9655077 wi-presentation-111012035448-phpapp01
]]>
]]> Wed, 12 Oct 2011 03:54:46 GMT /slideshow/wi-presentation/9655077 shekarpour@slideshare.net(shekarpour) Wi presentation shekarpour <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/wi-presentation-111012035448-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Wi presentation from Saeedeh Shekarpour
]]> 504 2 https://cdn.slidesharecdn.com/ss_thumbnails/wi-presentation-111012035448-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-shekarpour-48x48.jpg?cb=1682301117 I have spent the three and half years of my PhD in the field of Question Answering on Interlinked Data. During my PhD, I worked with the AKSW research group (a leading group in Semantic Web). In addition to gaining experience in the field of Semantic Web while working with this group, I initiated a project called SINA (a Semantic Search Engine over Interlinked Data). I am interested in pursuing advanced research in the following fields: Question Answering Semantic Search Semantic Web Information Retrieval Statistical Methods https://cdn.slidesharecdn.com/ss_thumbnails/aaai-make-190403162451-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/metrics-for-evaluating-quality-of-embeddings-for-ontological-concepts/139431216 Metrics for Evaluating... https://cdn.slidesharecdn.com/ss_thumbnails/cevo2-190202133718-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/cevo-comprehensive-event-ontology-enhancing-cognitive-annotation-on-relations/130283497 CEVO: Comprehensive EV... https://cdn.slidesharecdn.com/ss_thumbnails/aqualitytype-awareannotatedcorpusandlexiconforharassmentresearch-180528072046-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/a-quality-type-aware-annotated-corpus-and-lexicon-for-harassment-research/99168332 A quality type aware a...