ºÝºÝߣshows by User: shenghuiwang / http://www.slideshare.net/images/logo.gif ºÝºÝߣshows by User: shenghuiwang / Thu, 12 Sep 2019 09:18:33 GMT ºÝºÝߣShare feed for ºÝºÝߣshows by User: shenghuiwang Non-parametric Subject Prediction /slideshow/nonparametric-subject-prediction/171126877 oclctpdl2019-190912091833
Automatic subject prediction is a desirable feature for modern digital library systems, as manual indexing can no longer cope with the rapid growth of digital collections. This is an ``extreme multi-label classification'' problem, where the objective is to assign a small subset of the most relevant subjects from an extremely large label set. Data sparsity and model scalability are the major challenges we need to address to solve it automatically. In this paper, we describe an efficient and effective embedding method that embeds terms, subjects and documents into the same semantic space, where similarity can be computed easily. We then propose a novel Non-Parametric Subject Prediction (NPSP) method and show how effectively it predicts even very specialised subjects, which are associated with few documents in the training set and are not predicted by state-of-the-art classifiers. ]]>
Automatic subject prediction is a desirable feature for modern digital library systems, as manual indexing can no longer cope with the rapid growth of digital collections. This is an ``extreme multi-label classification'' problem, where the objective is to assign a small subset of the most relevant subjects from an extremely large label set. Data sparsity and model scalability are the major challenges we need to address to solve it automatically. In this paper, we describe an efficient and effective embedding method that embeds terms, subjects and documents into the same semantic space, where similarity can be computed easily. We then propose a novel Non-Parametric Subject Prediction (NPSP) method and show how effectively it predicts even very specialised subjects, which are associated with few documents in the training set and are not predicted by state-of-the-art classifiers. ]]> Thu, 12 Sep 2019 09:18:33 GMT /slideshow/nonparametric-subject-prediction/171126877 shenghuiwang@slideshare.net(shenghuiwang) Non-parametric Subject Prediction shenghuiwang Automatic subject prediction is a desirable feature for modern digital library systems, as manual indexing can no longer cope with the rapid growth of digital collections. This is an ``extreme multi-label classification'' problem, where the objective is to assign a small subset of the most relevant subjects from an extremely large label set. Data sparsity and model scalability are the major challenges we need to address to solve it automatically. In this paper, we describe an efficient and effective embedding method that embeds terms, subjects and documents into the same semantic space, where similarity can be computed easily. We then propose a novel Non-Parametric Subject Prediction (NPSP) method and show how effectively it predicts even very specialised subjects, which are associated with few documents in the training set and are not predicted by state-of-the-art classifiers. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/oclctpdl2019-190912091833-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Automatic subject prediction is a desirable feature for modern digital library systems, as manual indexing can no longer cope with the rapid growth of digital collections. This is an ``extreme multi-label classification&#39;&#39; problem, where the objective is to assign a small subset of the most relevant subjects from an extremely large label set. Data sparsity and model scalability are the major challenges we need to address to solve it automatically. In this paper, we describe an efficient and effective embedding method that embeds terms, subjects and documents into the same semantic space, where similarity can be computed easily. We then propose a novel Non-Parametric Subject Prediction (NPSP) method and show how effectively it predicts even very specialised subjects, which are associated with few documents in the training set and are not predicted by state-of-the-art classifiers.
Non-parametric Subject Prediction from Shenghui Wang
]]> 263 1 https://cdn.slidesharecdn.com/ss_thumbnails/oclctpdl2019-190912091833-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 Our journey with semantic embedding /slideshow/our-journey-with-semantic-embedding/72615398 knowescape2017-170227104715
Fourth Annual KnoweScape Conference (KnowEscape2017) http://knowescape.org/knowescape2017/]]>
Fourth Annual KnoweScape Conference (KnowEscape2017) http://knowescape.org/knowescape2017/]]> Mon, 27 Feb 2017 10:47:15 GMT /slideshow/our-journey-with-semantic-embedding/72615398 shenghuiwang@slideshare.net(shenghuiwang) Our journey with semantic embedding shenghuiwang Fourth Annual KnoweScape Conference (KnowEscape2017) http://knowescape.org/knowescape2017/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/knowescape2017-170227104715-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Fourth Annual KnoweScape Conference (KnowEscape2017) http://knowescape.org/knowescape2017/
Our journey with semantic embedding from Shenghui Wang
]]> 1931 5 https://cdn.slidesharecdn.com/ss_thumbnails/knowescape2017-170227104715-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 Linking entities via semantic indexing /slideshow/linking-entities-via-semantic-indexing/72614781 semanticindexingemearc17-170227102951
OCLC EMEA Regional Council Meeting, Berlin, 21-22 Feb 2017]]>
OCLC EMEA Regional Council Meeting, Berlin, 21-22 Feb 2017]]> Mon, 27 Feb 2017 10:29:51 GMT /slideshow/linking-entities-via-semantic-indexing/72614781 shenghuiwang@slideshare.net(shenghuiwang) Linking entities via semantic indexing shenghuiwang OCLC EMEA Regional Council Meeting, Berlin, 21-22 Feb 2017 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/semanticindexingemearc17-170227102951-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> OCLC EMEA Regional Council Meeting, Berlin, 21-22 Feb 2017
Linking entities via semantic indexing from Shenghui Wang
]]> 1829 4 https://cdn.slidesharecdn.com/ss_thumbnails/semanticindexingemearc17-170227102951-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 indexing for KOS /slideshow/semantic-indexing-for-kos/72138067 maltafeb2017-170214143624
This is our presentation given at the KnoweScape Workshop "Observatory for Knowledge Organisation Systems", Valletta, Malta, 1-3 Feb 2017]]>
This is our presentation given at the KnoweScape Workshop "Observatory for Knowledge Organisation Systems", Valletta, Malta, 1-3 Feb 2017]]> Tue, 14 Feb 2017 14:36:24 GMT /slideshow/semantic-indexing-for-kos/72138067 shenghuiwang@slideshare.net(shenghuiwang) Semantic indexing for KOS shenghuiwang This is our presentation given at the KnoweScape Workshop "Observatory for Knowledge Organisation Systems", Valletta, Malta, 1-3 Feb 2017 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/maltafeb2017-170214143624-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This is our presentation given at the KnoweScape Workshop &quot;Observatory for Knowledge Organisation Systems&quot;, Valletta, Malta, 1-3 Feb 2017
Semantic indexing for KOS from Shenghui Wang
]]> 1744 2 https://cdn.slidesharecdn.com/ss_thumbnails/maltafeb2017-170214143624-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 Contextualization of topics - browsing through terms, authors, journals and cluster allocations /slideshow/contextualization-of-topics-browsing-through-terms-authors-journals-and-cluster-allocations/50803947 ariadne-150722132711-lva1-app6891
Presentation at the 15th International Society of Scientometrics and Informetrics Conference, 29 June to 4 July, Istanbul, Turkey (http://www.issi2015.org).]]>
Presentation at the 15th International Society of Scientometrics and Informetrics Conference, 29 June to 4 July, Istanbul, Turkey (http://www.issi2015.org).]]> Wed, 22 Jul 2015 13:27:11 GMT /slideshow/contextualization-of-topics-browsing-through-terms-authors-journals-and-cluster-allocations/50803947 shenghuiwang@slideshare.net(shenghuiwang) Contextualization of topics - browsing through terms, authors, journals and cluster allocations shenghuiwang Presentation at the 15th International Society of Scientometrics and Informetrics Conference, 29 June to 4 July, Istanbul, Turkey (http://www.issi2015.org). <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ariadne-150722132711-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Presentation at the 15th International Society of Scientometrics and Informetrics Conference, 29 June to 4 July, Istanbul, Turkey (http://www.issi2015.org).
Contextualization of topics - browsing through terms, authors, journals and cluster allocations from Shenghui Wang
]]> 315 7 https://cdn.slidesharecdn.com/ss_thumbnails/ariadne-150722132711-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 Exploring a world of networked information built from free-text metadata /slideshow/elag/49268472 elag-150611131217-lva1-app6892
Ariadne: interactive context viewer for bibliographic data]]>
Ariadne: interactive context viewer for bibliographic data]]> Thu, 11 Jun 2015 13:12:17 GMT /slideshow/elag/49268472 shenghuiwang@slideshare.net(shenghuiwang) Exploring a world of networked information built from free-text metadata shenghuiwang Ariadne: interactive context viewer for bibliographic data <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/elag-150611131217-lva1-app6892-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Ariadne: interactive context viewer for bibliographic data
Exploring a world of networked information built from free-text metadata from Shenghui Wang
]]> 2943 4 https://cdn.slidesharecdn.com/ss_thumbnails/elag-150611131217-lva1-app6892-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 Ariadne's Thread -- Exploring a world of networked information built from free-text metadata /slideshow/knaw/46442866 knaw-150330054612-conversion-gate01
Most of the current interfaces to digital libraries are built on keyword-based search and list-based presentation. For users who do not have specific items to search for but would rather explore not-yet-familiar topics, it is not easy to figure out to what extend and on which aspects the returned records match the query. Users have to try different combinations of keywords to narrow down or broaden the search space in the hope of getting useful results in the end. In this talk, we will present a web interface that provides users an opportunity to interactively and visually explore the context of queries. In this interface, after entering a query, a contextual view about the query is visualised, where the most related journals, authors, subject headings, publishers, topical terms, etc. are positioned in 2D based on their relatedness to the query and among each other. By clicking any of these nodes, a new visualisation about the selected one is presented. With this click-through style, the users could get visual contexts about their selected entities (journal, author, topical terms, etc.) and shift their interests by choosing interested (types of) entities to investigate further. At any stop, a search in WorldCat.org with the currently focused entity (a topical word, a author or a journal) will return the most matched results (judged by the standard WorldCat search engine). We implemented this interface over WorldCat, the world largest bibliographic database. To guarantee the responsiveness of this interactive interface, we adopt a two-step approach: an off-line preparation phase with an on-line process. Off-line, we build the semantic representation of each entity where Random Projection is used to vigorously reduce dimensionality (from 6 million to 600). In the on-line interface terms from a query are compared to entities in the reduced semantic matrix where reciprocal relatedness is used to select genuine matches. The number of hits is further reduced to render a network layout easy to overview and navigate. In the end, we can investigate the relations between roughly 6 million topical terms, 5 million authors, 1 million subject headings 1000 Dewey decimal codes and 1.7 million publishers.]]>
Most of the current interfaces to digital libraries are built on keyword-based search and list-based presentation. For users who do not have specific items to search for but would rather explore not-yet-familiar topics, it is not easy to figure out to what extend and on which aspects the returned records match the query. Users have to try different combinations of keywords to narrow down or broaden the search space in the hope of getting useful results in the end. In this talk, we will present a web interface that provides users an opportunity to interactively and visually explore the context of queries. In this interface, after entering a query, a contextual view about the query is visualised, where the most related journals, authors, subject headings, publishers, topical terms, etc. are positioned in 2D based on their relatedness to the query and among each other. By clicking any of these nodes, a new visualisation about the selected one is presented. With this click-through style, the users could get visual contexts about their selected entities (journal, author, topical terms, etc.) and shift their interests by choosing interested (types of) entities to investigate further. At any stop, a search in WorldCat.org with the currently focused entity (a topical word, a author or a journal) will return the most matched results (judged by the standard WorldCat search engine). We implemented this interface over WorldCat, the world largest bibliographic database. To guarantee the responsiveness of this interactive interface, we adopt a two-step approach: an off-line preparation phase with an on-line process. Off-line, we build the semantic representation of each entity where Random Projection is used to vigorously reduce dimensionality (from 6 million to 600). In the on-line interface terms from a query are compared to entities in the reduced semantic matrix where reciprocal relatedness is used to select genuine matches. The number of hits is further reduced to render a network layout easy to overview and navigate. In the end, we can investigate the relations between roughly 6 million topical terms, 5 million authors, 1 million subject headings 1000 Dewey decimal codes and 1.7 million publishers.]]> Mon, 30 Mar 2015 05:46:12 GMT /slideshow/knaw/46442866 shenghuiwang@slideshare.net(shenghuiwang) Ariadne's Thread -- Exploring a world of networked information built from free-text metadata shenghuiwang Most of the current interfaces to digital libraries are built on keyword-based search and list-based presentation. For users who do not have specific items to search for but would rather explore not-yet-familiar topics, it is not easy to figure out to what extend and on which aspects the returned records match the query. Users have to try different combinations of keywords to narrow down or broaden the search space in the hope of getting useful results in the end. In this talk, we will present a web interface that provides users an opportunity to interactively and visually explore the context of queries. In this interface, after entering a query, a contextual view about the query is visualised, where the most related journals, authors, subject headings, publishers, topical terms, etc. are positioned in 2D based on their relatedness to the query and among each other. By clicking any of these nodes, a new visualisation about the selected one is presented. With this click-through style, the users could get visual contexts about their selected entities (journal, author, topical terms, etc.) and shift their interests by choosing interested (types of) entities to investigate further. At any stop, a search in WorldCat.org with the currently focused entity (a topical word, a author or a journal) will return the most matched results (judged by the standard WorldCat search engine). We implemented this interface over WorldCat, the world largest bibliographic database. To guarantee the responsiveness of this interactive interface, we adopt a two-step approach: an off-line preparation phase with an on-line process. Off-line, we build the semantic representation of each entity where Random Projection is used to vigorously reduce dimensionality (from 6 million to 600). In the on-line interface terms from a query are compared to entities in the reduced semantic matrix where reciprocal relatedness is used to select genuine matches. The number of hits is further reduced to render a network layout easy to overview and navigate. In the end, we can investigate the relations between roughly 6 million topical terms, 5 million authors, 1 million subject headings 1000 Dewey decimal codes and 1.7 million publishers. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/knaw-150330054612-conversion-gate01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Most of the current interfaces to digital libraries are built on keyword-based search and list-based presentation. For users who do not have specific items to search for but would rather explore not-yet-familiar topics, it is not easy to figure out to what extend and on which aspects the returned records match the query. Users have to try different combinations of keywords to narrow down or broaden the search space in the hope of getting useful results in the end. In this talk, we will present a web interface that provides users an opportunity to interactively and visually explore the context of queries. In this interface, after entering a query, a contextual view about the query is visualised, where the most related journals, authors, subject headings, publishers, topical terms, etc. are positioned in 2D based on their relatedness to the query and among each other. By clicking any of these nodes, a new visualisation about the selected one is presented. With this click-through style, the users could get visual contexts about their selected entities (journal, author, topical terms, etc.) and shift their interests by choosing interested (types of) entities to investigate further. At any stop, a search in WorldCat.org with the currently focused entity (a topical word, a author or a journal) will return the most matched results (judged by the standard WorldCat search engine). We implemented this interface over WorldCat, the world largest bibliographic database. To guarantee the responsiveness of this interactive interface, we adopt a two-step approach: an off-line preparation phase with an on-line process. Off-line, we build the semantic representation of each entity where Random Projection is used to vigorously reduce dimensionality (from 6 million to 600). In the on-line interface terms from a query are compared to entities in the reduced semantic matrix where reciprocal relatedness is used to select genuine matches. The number of hits is further reduced to render a network layout easy to overview and navigate. In the end, we can investigate the relations between roughly 6 million topical terms, 5 million authors, 1 million subject headings 1000 Dewey decimal codes and 1.7 million publishers.
Ariadne's Thread -- Exploring a world of networked information built from free-text metadata from Shenghui Wang
]]> 432 2 https://cdn.slidesharecdn.com/ss_thumbnails/knaw-150330054612-conversion-gate01-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 Learning Concept Mappings from Instance Similarity /slideshow/learning-14285955/14285955 learning-120914042347-phpapp01
]]>
]]> Fri, 14 Sep 2012 04:23:45 GMT /slideshow/learning-14285955/14285955 shenghuiwang@slideshare.net(shenghuiwang) Learning Concept Mappings from Instance Similarity shenghuiwang <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/learning-120914042347-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Learning Concept Mappings from Instance Similarity from Shenghui Wang
]]> 439 3 https://cdn.slidesharecdn.com/ss_thumbnails/learning-120914042347-phpapp01-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 Measuring the dynamic �bi-directional influence between content and social networks /slideshow/measuring-the-dynamic-bidirectional-influence-between-content-and-social-networks/5814398 slidesiswc2010-12900245624849-phpapp01
]]>
]]> Wed, 17 Nov 2010 14:11:41 GMT /slideshow/measuring-the-dynamic-bidirectional-influence-between-content-and-social-networks/5814398 shenghuiwang@slideshare.net(shenghuiwang) Measuring the dynamic �bi-directional influence between content and social networks shenghuiwang <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/slidesiswc2010-12900245624849-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Measuring the dynamic bi-directional influence between content and social networks from Shenghui Wang
]]> 513 3 https://cdn.slidesharecdn.com/ss_thumbnails/slidesiswc2010-12900245624849-phpapp01-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 Similarity Features, and their Role in Concept Alignment Learning /slideshow/similarity-features-and-their-role-in-concept-alignment-learning-5564231/5564231 slidessemapro-101026053232-phpapp01
]]>
]]> Tue, 26 Oct 2010 05:32:21 GMT /slideshow/similarity-features-and-their-role-in-concept-alignment-learning-5564231/5564231 shenghuiwang@slideshare.net(shenghuiwang) Similarity Features, and their Role in Concept Alignment Learning shenghuiwang <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/slidessemapro-101026053232-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Similarity Features, and their Role in Concept Alignment Learning from Shenghui Wang
]]> 311 2 https://cdn.slidesharecdn.com/ss_thumbnails/slidessemapro-101026053232-phpapp01-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 What is concept dirft and how to measure it? /shenghuiwang/what-is-concept-dirft-and-how-to-measure-it slidesekaw2010-101024173948-phpapp01
]]>
]]> Sun, 24 Oct 2010 17:39:28 GMT /shenghuiwang/what-is-concept-dirft-and-how-to-measure-it shenghuiwang@slideshare.net(shenghuiwang) What is concept dirft and how to measure it? shenghuiwang <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/slidesekaw2010-101024173948-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
What is concept dirft and how to measure it? from Shenghui Wang
]]> 1332 3 https://cdn.slidesharecdn.com/ss_thumbnails/slidesekaw2010-101024173948-phpapp01-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 ICA ºÝºÝߣs /slideshow/ica-slides/5345858 temporalslides-12861088543481-phpapp02
2010 Conference of the International Communication Association]]>
2010 Conference of the International Communication Association]]> Sun, 03 Oct 2010 07:32:49 GMT /slideshow/ica-slides/5345858 shenghuiwang@slideshare.net(shenghuiwang) ICA ºÝºÝߣs shenghuiwang 2010 Conference of the International Communication Association <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/temporalslides-12861088543481-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 2010 Conference of the International Communication Association
ICA ºÝºÝߣs from Shenghui Wang
]]> 843 3 https://cdn.slidesharecdn.com/ss_thumbnails/temporalslides-12861088543481-phpapp02-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 ECCS 2010 /slideshow/eccs-2010/5192747 slideeccs-100913141841-phpapp01
]]>
]]> Mon, 13 Sep 2010 14:18:32 GMT /slideshow/eccs-2010/5192747 shenghuiwang@slideshare.net(shenghuiwang) ECCS 2010 shenghuiwang <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/slideeccs-100913141841-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
ECCS 2010 from Shenghui Wang
]]> 513 1 https://cdn.slidesharecdn.com/ss_thumbnails/slideeccs-100913141841-phpapp01-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 Study concept drift in political ontologies /slideshow/dynamics-4691761/4691761 dynamics-100706052540-phpapp02
]]>
]]> Tue, 06 Jul 2010 05:25:37 GMT /slideshow/dynamics-4691761/4691761 shenghuiwang@slideshare.net(shenghuiwang) Study concept drift in political ontologies shenghuiwang <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/dynamics-100706052540-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Study concept drift in political ontologies from Shenghui Wang
]]> 242 2 https://cdn.slidesharecdn.com/ss_thumbnails/dynamics-100706052540-phpapp02-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 https://cdn.slidesharecdn.com/profile-photo-shenghuiwang-48x48.jpg?cb=1568279840 http://www.few.vu.nl/~swang https://cdn.slidesharecdn.com/ss_thumbnails/oclctpdl2019-190912091833-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/nonparametric-subject-prediction/171126877 Non-parametric Subject... https://cdn.slidesharecdn.com/ss_thumbnails/knowescape2017-170227104715-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/our-journey-with-semantic-embedding/72615398 Our journey with seman... https://cdn.slidesharecdn.com/ss_thumbnails/semanticindexingemearc17-170227102951-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/linking-entities-via-semantic-indexing/72614781 Linking entities via s...