�ݺ�ߣshows by User: gdm3003

�ݺ�ߣshows by User: gdm3003 / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: gdm3003 / Thu, 11 Oct 2018 20:58:46 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: gdm3003 SEMAC Graph Node Embeddings for Link Prediction /slideshow/semac-graph-node-embeddings-for-link-prediction/119148104 slides-export-181011205847
We present a new graph representation learning approach called SEMAC that jointly exploits fine-grained node features as well as the overall graph topology. In contrast to the SGNS or SVD methods espoused in previous representation-based studies, our model represents nodes in terms of subgraph embeddings acquired via a form of convex matrix completion to iteratively reduce the rank, and thereby, more effectively eliminate noise in the representation. Thus, subgraph embeddings and convex matrix completion are elegantly integrated into a novel link prediction framework.]]>
We present a new graph representation learning approach called SEMAC that jointly exploits fine-grained node features as well as the overall graph topology. In contrast to the SGNS or SVD methods espoused in previous representation-based studies, our model represents nodes in terms of subgraph embeddings acquired via a form of convex matrix completion to iteratively reduce the rank, and thereby, more effectively eliminate noise in the representation. Thus, subgraph embeddings and convex matrix completion are elegantly integrated into a novel link prediction framework.]]> Thu, 11 Oct 2018 20:58:46 GMT /slideshow/semac-graph-node-embeddings-for-link-prediction/119148104 gdm3003@slideshare.net(gdm3003) SEMAC Graph Node Embeddings for Link Prediction gdm3003 We present a new graph representation learning approach called SEMAC that jointly exploits fine-grained node features as well as the overall graph topology. In contrast to the SGNS or SVD methods espoused in previous representation-based studies, our model represents nodes in terms of subgraph embeddings acquired via a form of convex matrix completion to iteratively reduce the rank, and thereby, more effectively eliminate noise in the representation. Thus, subgraph embeddings and convex matrix completion are elegantly integrated into a novel link prediction framework. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/slides-export-181011205847-thumbnail.jpg?width=120&height=120&fit=bounds" /> We present a new graph representation learning approach called SEMAC that jointly exploits fine-grained node features as well as the overall graph topology. In contrast to the SGNS or SVD methods espoused in previous representation-based studies, our model represents nodes in terms of subgraph embeddings acquired via a form of convex matrix completion to iteratively reduce the rank, and thereby, more effectively eliminate noise in the representation. Thus, subgraph embeddings and convex matrix completion are elegantly integrated into a novel link prediction framework.

SEMAC Graph Node Embeddings for Link Prediction from Gerard de Melo

]]> 938 2 https://cdn.slidesharecdn.com/ss_thumbnails/slides-export-181011205847-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 How to Manage your Research /gdm3003/how-to-manage-your-research how-to-manage-your-research-160328114041
While traditional scholarship has tended to emphasize thorough reading, reflection, and learning, many researchers nowadays – both in academia and industry – find themselves in a fast-paced and demanding environment. A successful research career crucially depends on management-related skills, and devoting some time to such skills is likely to pay off very quickly. One important example is time and task management, which is critical when there are numerous conflicting demands and opportunities. Another example is being able to cope with challenges and failure. Researchers also need to be creative and bold in defending their ideas. This talk provides an overview of these and other skills that are vital in modern research environments.]]>
While traditional scholarship has tended to emphasize thorough reading, reflection, and learning, many researchers nowadays – both in academia and industry – find themselves in a fast-paced and demanding environment. A successful research career crucially depends on management-related skills, and devoting some time to such skills is likely to pay off very quickly. One important example is time and task management, which is critical when there are numerous conflicting demands and opportunities. Another example is being able to cope with challenges and failure. Researchers also need to be creative and bold in defending their ideas. This talk provides an overview of these and other skills that are vital in modern research environments.]]> Mon, 28 Mar 2016 11:40:41 GMT /gdm3003/how-to-manage-your-research gdm3003@slideshare.net(gdm3003) How to Manage your Research gdm3003 While traditional scholarship has tended to emphasize thorough reading, reflection, and learning, many researchers nowadays – both in academia and industry – find themselves in a fast-paced and demanding environment. A successful research career crucially depends on management-related skills, and devoting some time to such skills is likely to pay off very quickly. One important example is time and task management, which is critical when there are numerous conflicting demands and opportunities. Another example is being able to cope with challenges and failure. Researchers also need to be creative and bold in defending their ideas. This talk provides an overview of these and other skills that are vital in modern research environments. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/how-to-manage-your-research-160328114041-thumbnail.jpg?width=120&height=120&fit=bounds" /> While traditional scholarship has tended to emphasize thorough reading, reflection, and learning, many researchers nowadays – both in academia and industry – find themselves in a fast-paced and demanding environment. A successful research career crucially depends on management-related skills, and devoting some time to such skills is likely to pay off very quickly. One important example is time and task management, which is critical when there are numerous conflicting demands and opportunities. Another example is being able to cope with challenges and failure. Researchers also need to be creative and bold in defending their ideas. This talk provides an overview of these and other skills that are vital in modern research environments.

How to Manage your Research from Gerard de Melo

]]> 2329 7 https://cdn.slidesharecdn.com/ss_thumbnails/how-to-manage-your-research-160328114041-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 Knowlywood: Mining Activity Knowledge from Hollywood Narratives /slideshow/knowlywood-mining-activity-knowledge-from-hollywood-narratives/55533408 knowlywood-mining-activity-knowledge-from-hollywood-narratives-151126065134-lva1-app6891
Knowlywood is a new knowledge graph mined from movies, TV series, and literature. It provides commonsense knowledge about human activities, e.g. participants, preceding and following activities, and so on.]]>
Knowlywood is a new knowledge graph mined from movies, TV series, and literature. It provides commonsense knowledge about human activities, e.g. participants, preceding and following activities, and so on.]]> Thu, 26 Nov 2015 06:51:34 GMT /slideshow/knowlywood-mining-activity-knowledge-from-hollywood-narratives/55533408 gdm3003@slideshare.net(gdm3003) Knowlywood: Mining Activity Knowledge from Hollywood Narratives gdm3003 Knowlywood is a new knowledge graph mined from movies, TV series, and literature. It provides commonsense knowledge about human activities, e.g. participants, preceding and following activities, and so on. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/knowlywood-mining-activity-knowledge-from-hollywood-narratives-151126065134-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds" /> Knowlywood is a new knowledge graph mined from movies, TV series, and literature. It provides commonsense knowledge about human activities, e.g. participants, preceding and following activities, and so on.

Knowlywood: Mining Activity Knowledge from Hollywood Narratives from Gerard de Melo

]]> 848 5 https://cdn.slidesharecdn.com/ss_thumbnails/knowlywood-mining-activity-knowledge-from-hollywood-narratives-151126065134-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 Learning Multilingual Semantics from Big Data on the Web /gdm3003/learning-multilingual-semantics-from-big-data-on-the-web learningmultilingualsemanticsfrombigdataontheweb-150730153157-lva1-app6892
�ݺ�ߣs from Keynote at ACL 2015 Semantics-Driven Statistical Machine Translation (S2MT) Workshop]]>
�ݺ�ߣs from Keynote at ACL 2015 Semantics-Driven Statistical Machine Translation (S2MT) Workshop]]> Thu, 30 Jul 2015 15:31:57 GMT /gdm3003/learning-multilingual-semantics-from-big-data-on-the-web gdm3003@slideshare.net(gdm3003) Learning Multilingual Semantics from Big Data on the Web gdm3003 �ݺ�ߣs from Keynote at ACL 2015 Semantics-Driven Statistical Machine Translation (S2MT) Workshop <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/learningmultilingualsemanticsfrombigdataontheweb-150730153157-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds" /> �ݺ�ߣs from Keynote at ACL 2015 Semantics-Driven Statistical Machine Translation (S2MT) Workshop

Learning Multilingual Semantics from Big Data on the Web from Gerard de Melo

]]> 1230 7 https://cdn.slidesharecdn.com/ss_thumbnails/learningmultilingualsemanticsfrombigdataontheweb-150730153157-lva1-app6892-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 From Big Data to Valuable Knowledge /slideshow/from-big-data-to-valuable-knowledge/49395862 panel-150615084111-lva1-app6891
Big Data is more than just hype. The vast quantities of data now available have led to two important challenges that are fundamentally changing the way we develop data-intensive systems. The first is at the data management level, where we are finally moving beyond vanilla MapReduce towards infrastructure that allows for more flexible data processing pipelines. The second challenge is transitioning from quantity to quality and distilling genuine knowledge from the raw data. For this, we still need innovative algorithms that facilitate data cleaning, unsupervised and semi-supervised learning, knowledge harvesting, and knowledge integration. Examples include data integration, and large-scale knowledge bases such as UWN/MENTA, and collections of commonsense knowledge such as WebChild.]]>
Big Data is more than just hype. The vast quantities of data now available have led to two important challenges that are fundamentally changing the way we develop data-intensive systems. The first is at the data management level, where we are finally moving beyond vanilla MapReduce towards infrastructure that allows for more flexible data processing pipelines. The second challenge is transitioning from quantity to quality and distilling genuine knowledge from the raw data. For this, we still need innovative algorithms that facilitate data cleaning, unsupervised and semi-supervised learning, knowledge harvesting, and knowledge integration. Examples include data integration, and large-scale knowledge bases such as UWN/MENTA, and collections of commonsense knowledge such as WebChild.]]> Mon, 15 Jun 2015 08:41:11 GMT /slideshow/from-big-data-to-valuable-knowledge/49395862 gdm3003@slideshare.net(gdm3003) From Big Data to Valuable Knowledge gdm3003 Big Data is more than just hype. The vast quantities of data now available have led to two important challenges that are fundamentally changing the way we develop data-intensive systems. The first is at the data management level, where we are finally moving beyond vanilla MapReduce towards infrastructure that allows for more flexible data processing pipelines. The second challenge is transitioning from quantity to quality and distilling genuine knowledge from the raw data. For this, we still need innovative algorithms that facilitate data cleaning, unsupervised and semi-supervised learning, knowledge harvesting, and knowledge integration. Examples include data integration, and large-scale knowledge bases such as UWN/MENTA, and collections of commonsense knowledge such as WebChild. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/panel-150615084111-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds" /> Big Data is more than just hype. The vast quantities of data now available have led to two important challenges that are fundamentally changing the way we develop data-intensive systems. The first is at the data management level, where we are finally moving beyond vanilla MapReduce towards infrastructure that allows for more flexible data processing pipelines. The second challenge is transitioning from quantity to quality and distilling genuine knowledge from the raw data. For this, we still need innovative algorithms that facilitate data cleaning, unsupervised and semi-supervised learning, knowledge harvesting, and knowledge integration. Examples include data integration, and large-scale knowledge bases such as UWN/MENTA, and collections of commonsense knowledge such as WebChild.

From Big Data to Valuable Knowledge from Gerard de Melo

]]> 1033 3 https://cdn.slidesharecdn.com/ss_thumbnails/panel-150615084111-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 Scalable Learning Technologies for Big Data Mining /slideshow/scalable-learning-technologies-for-big-data-mining/49395498 big-data-mining-tutorial-dasfaa2015-slides-150615083043-lva1-app6892
These are slides of a tutorial by Gerard de Melo and Aparna Varde presented at the DASFAA 2015 conference. As data expands into big data, enhanced or entirely novel data mining algorithms often become necessary. The real value of big data is often only exposed when we can adequately mine and learn from it. We provide an overview of new scalable techniques for knowledge discovery. Our focus is on the areas of cloud data mining and machine learning, semi-supervised processing, and deep learning. We also give practical advice for choosing among different methods and discuss open research problems and concerns.]]>
These are slides of a tutorial by Gerard de Melo and Aparna Varde presented at the DASFAA 2015 conference. As data expands into big data, enhanced or entirely novel data mining algorithms often become necessary. The real value of big data is often only exposed when we can adequately mine and learn from it. We provide an overview of new scalable techniques for knowledge discovery. Our focus is on the areas of cloud data mining and machine learning, semi-supervised processing, and deep learning. We also give practical advice for choosing among different methods and discuss open research problems and concerns.]]> Mon, 15 Jun 2015 08:30:43 GMT /slideshow/scalable-learning-technologies-for-big-data-mining/49395498 gdm3003@slideshare.net(gdm3003) Scalable Learning Technologies for Big Data Mining gdm3003 These are slides of a tutorial by Gerard de Melo and Aparna Varde presented at the DASFAA 2015 conference. As data expands into big data, enhanced or entirely novel data mining algorithms often become necessary. The real value of big data is often only exposed when we can adequately mine and learn from it. We provide an overview of new scalable techniques for knowledge discovery. Our focus is on the areas of cloud data mining and machine learning, semi-supervised processing, and deep learning. We also give practical advice for choosing among different methods and discuss open research problems and concerns. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/big-data-mining-tutorial-dasfaa2015-slides-150615083043-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds" /> These are slides of a tutorial by Gerard de Melo and Aparna Varde presented at the DASFAA 2015 conference. As data expands into big data, enhanced or entirely novel data mining algorithms often become necessary. The real value of big data is often only exposed when we can adequately mine and learn from it. We provide an overview of new scalable techniques for knowledge discovery. Our focus is on the areas of cloud data mining and machine learning, semi-supervised processing, and deep learning. We also give practical advice for choosing among different methods and discuss open research problems and concerns.

Scalable Learning Technologies for Big Data Mining from Gerard de Melo

]]> 1741 5 https://cdn.slidesharecdn.com/ss_thumbnails/big-data-mining-tutorial-dasfaa2015-slides-150615083043-lva1-app6892-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 Searching the Web of Data (Tutorial) /slideshow/searching-the-web-of-data-tutorial/49395398 ecir2013-150615082819-lva1-app6892
These are slides of a tutorial at ECIR by Gerard de Melo and Katja Hose. Search is currently undergoing a major paradigm shift away from the traditional document-centric “10 blue links” towards more explicit and actionable information. Recent advances in this area are Google’s Knowledge Graph, Virtual Personal Assistants such as Siri and Google Now, as well as the now ubiquitous entity-oriented vertical search results for places, products, etc. Apart from novel query understanding methods, these developments are largely driven by structured data that is blended into the Web Search experience. We discuss efficient indexing and query processing techniques to work with large amounts of structured data. Finally, we present query interpretation and understanding methods to map user queries to these structured data sources.]]>
These are slides of a tutorial at ECIR by Gerard de Melo and Katja Hose. Search is currently undergoing a major paradigm shift away from the traditional document-centric “10 blue links” towards more explicit and actionable information. Recent advances in this area are Google’s Knowledge Graph, Virtual Personal Assistants such as Siri and Google Now, as well as the now ubiquitous entity-oriented vertical search results for places, products, etc. Apart from novel query understanding methods, these developments are largely driven by structured data that is blended into the Web Search experience. We discuss efficient indexing and query processing techniques to work with large amounts of structured data. Finally, we present query interpretation and understanding methods to map user queries to these structured data sources.]]> Mon, 15 Jun 2015 08:28:19 GMT /slideshow/searching-the-web-of-data-tutorial/49395398 gdm3003@slideshare.net(gdm3003) Searching the Web of Data (Tutorial) gdm3003 These are slides of a tutorial at ECIR by Gerard de Melo and Katja Hose. Search is currently undergoing a major paradigm shift away from the traditional document-centric “10 blue links” towards more explicit and actionable information. Recent advances in this area are Google’s Knowledge Graph, Virtual Personal Assistants such as Siri and Google Now, as well as the now ubiquitous entity-oriented vertical search results for places, products, etc. Apart from novel query understanding methods, these developments are largely driven by structured data that is blended into the Web Search experience. We discuss efficient indexing and query processing techniques to work with large amounts of structured data. Finally, we present query interpretation and understanding methods to map user queries to these structured data sources. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ecir2013-150615082819-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds" /> These are slides of a tutorial at ECIR by Gerard de Melo and Katja Hose. Search is currently undergoing a major paradigm shift away from the traditional document-centric “10 blue links” towards more explicit and actionable information. Recent advances in this area are Google’s Knowledge Graph, Virtual Personal Assistants such as Siri and Google Now, as well as the now ubiquitous entity-oriented vertical search results for places, products, etc. Apart from novel query understanding methods, these developments are largely driven by structured data that is blended into the Web Search experience. We discuss efficient indexing and query processing techniques to work with large amounts of structured data. Finally, we present query interpretation and understanding methods to map user queries to these structured data sources.

Searching the Web of Data (Tutorial) from Gerard de Melo

]]> 1918 6 https://cdn.slidesharecdn.com/ss_thumbnails/ecir2013-150615082819-lva1-app6892-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 From Linked Data to Tightly Integrated Data /slideshow/from-linked-data-to-tightly-integrated-data/40379914 fromlinkeddatatotightlyintegrateddata-141016222932-conversion-gate01
Invited Talk at the 3rd Workshop on Linked Data in Linguistics: Multilingual Knowledge Resources and Natural Language Processing. Reykjavik, Iceland, 27th May 2014 The ideas behind the Web of Linked Data have great allure. Apart from the prospect of large amounts of freely available data, we are also promised nearly effortless interoperability. Common data formats and protocols have indeed made it easier than ever to obtain and work with information from different sources simultaneously, opening up new opportunities in linguistics, library science, and many other areas. In this talk, however, I argue that the true potential of Linked Data can only be appreciated when extensive cross-linkage and integration engenders an even higher degree of interconnectedness. This can take the form of shared identifiers, e.g. those based on Wikipedia and WordNet, which can be used to describe numerous forms of linguistic and commonsense knowledge. An alternative is to rely on sameAs and similarity links, which can automatically be discovered using scalable approaches like the LINDA algorithm but need to be interpreted with great care, as we have observed in experimental studies. A closer level of linkage is achieved when resources are also connected at the taxonomic level, as exemplified by the MENTA approach to taxonomic data integration. Such integration means that one can buy into ecosystems already carrying a range of valuable pre-existing assets. Even more tightly integrated resources like Lexvo.org combine triples from multiple sources into unified, coherent knowledge bases. Finally, I also comment on how to address some remaining challenges that are still impeding a more widespread adoption of Linked Data on the Web. In the long run, I believe that such steps will lead us to significantly more tightly integrated Linked Data.]]>
Invited Talk at the 3rd Workshop on Linked Data in Linguistics: Multilingual Knowledge Resources and Natural Language Processing. Reykjavik, Iceland, 27th May 2014 The ideas behind the Web of Linked Data have great allure. Apart from the prospect of large amounts of freely available data, we are also promised nearly effortless interoperability. Common data formats and protocols have indeed made it easier than ever to obtain and work with information from different sources simultaneously, opening up new opportunities in linguistics, library science, and many other areas. In this talk, however, I argue that the true potential of Linked Data can only be appreciated when extensive cross-linkage and integration engenders an even higher degree of interconnectedness. This can take the form of shared identifiers, e.g. those based on Wikipedia and WordNet, which can be used to describe numerous forms of linguistic and commonsense knowledge. An alternative is to rely on sameAs and similarity links, which can automatically be discovered using scalable approaches like the LINDA algorithm but need to be interpreted with great care, as we have observed in experimental studies. A closer level of linkage is achieved when resources are also connected at the taxonomic level, as exemplified by the MENTA approach to taxonomic data integration. Such integration means that one can buy into ecosystems already carrying a range of valuable pre-existing assets. Even more tightly integrated resources like Lexvo.org combine triples from multiple sources into unified, coherent knowledge bases. Finally, I also comment on how to address some remaining challenges that are still impeding a more widespread adoption of Linked Data on the Web. In the long run, I believe that such steps will lead us to significantly more tightly integrated Linked Data.]]> Thu, 16 Oct 2014 22:29:32 GMT /slideshow/from-linked-data-to-tightly-integrated-data/40379914 gdm3003@slideshare.net(gdm3003) From Linked Data to Tightly Integrated Data gdm3003 Invited Talk at the 3rd Workshop on Linked Data in Linguistics: Multilingual Knowledge Resources and Natural Language Processing. Reykjavik, Iceland, 27th May 2014 The ideas behind the Web of Linked Data have great allure. Apart from the prospect of large amounts of freely available data, we are also promised nearly effortless interoperability. Common data formats and protocols have indeed made it easier than ever to obtain and work with information from different sources simultaneously, opening up new opportunities in linguistics, library science, and many other areas. In this talk, however, I argue that the true potential of Linked Data can only be appreciated when extensive cross-linkage and integration engenders an even higher degree of interconnectedness. This can take the form of shared identifiers, e.g. those based on Wikipedia and WordNet, which can be used to describe numerous forms of linguistic and commonsense knowledge. An alternative is to rely on sameAs and similarity links, which can automatically be discovered using scalable approaches like the LINDA algorithm but need to be interpreted with great care, as we have observed in experimental studies. A closer level of linkage is achieved when resources are also connected at the taxonomic level, as exemplified by the MENTA approach to taxonomic data integration. Such integration means that one can buy into ecosystems already carrying a range of valuable pre-existing assets. Even more tightly integrated resources like Lexvo.org combine triples from multiple sources into unified, coherent knowledge bases. Finally, I also comment on how to address some remaining challenges that are still impeding a more widespread adoption of Linked Data on the Web. In the long run, I believe that such steps will lead us to significantly more tightly integrated Linked Data. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/fromlinkeddatatotightlyintegrateddata-141016222932-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Invited Talk at the 3rd Workshop on Linked Data in Linguistics: Multilingual Knowledge Resources and Natural Language Processing. Reykjavik, Iceland, 27th May 2014 The ideas behind the Web of Linked Data have great allure. Apart from the prospect of large amounts of freely available data, we are also promised nearly effortless interoperability. Common data formats and protocols have indeed made it easier than ever to obtain and work with information from different sources simultaneously, opening up new opportunities in linguistics, library science, and many other areas. In this talk, however, I argue that the true potential of Linked Data can only be appreciated when extensive cross-linkage and integration engenders an even higher degree of interconnectedness. This can take the form of shared identifiers, e.g. those based on Wikipedia and WordNet, which can be used to describe numerous forms of linguistic and commonsense knowledge. An alternative is to rely on sameAs and similarity links, which can automatically be discovered using scalable approaches like the LINDA algorithm but need to be interpreted with great care, as we have observed in experimental studies. A closer level of linkage is achieved when resources are also connected at the taxonomic level, as exemplified by the MENTA approach to taxonomic data integration. Such integration means that one can buy into ecosystems already carrying a range of valuable pre-existing assets. Even more tightly integrated resources like Lexvo.org combine triples from multiple sources into unified, coherent knowledge bases. Finally, I also comment on how to address some remaining challenges that are still impeding a more widespread adoption of Linked Data on the Web. In the long run, I believe that such steps will lead us to significantly more tightly integrated Linked Data.

From Linked Data to Tightly Integrated Data from Gerard de Melo

]]> 1605 1 https://cdn.slidesharecdn.com/ss_thumbnails/fromlinkeddatatotightlyintegrateddata-141016222932-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 Information Extraction from Web-Scale N-Gram Data /slideshow/information-extraction-from-webscale-ngram-data/36028260 informationextractionfromweb-scalen-gramdata-140618124855-phpapp01
Search engines are increasingly relying on structured data to provide direct answers to certain types of queries. However, extracting such structured data from text is challenging, especially due to the scarcity of explicitly expressed knowledge. Even when relying on large document collections, pattern-based information extraction approaches typically expose only insufficient amounts of information. This paper evaluates to what extent n-gram statistics, derived from volumes of texts several orders of magnitude larger than typical corpora, can allow us to overcome this bottleneck. An extensive experimental evaluation is provided for three different binary relations, comparing different sources of n-gram data as well as different learning algorithms.]]>
Search engines are increasingly relying on structured data to provide direct answers to certain types of queries. However, extracting such structured data from text is challenging, especially due to the scarcity of explicitly expressed knowledge. Even when relying on large document collections, pattern-based information extraction approaches typically expose only insufficient amounts of information. This paper evaluates to what extent n-gram statistics, derived from volumes of texts several orders of magnitude larger than typical corpora, can allow us to overcome this bottleneck. An extensive experimental evaluation is provided for three different binary relations, comparing different sources of n-gram data as well as different learning algorithms.]]> Wed, 18 Jun 2014 12:48:55 GMT /slideshow/information-extraction-from-webscale-ngram-data/36028260 gdm3003@slideshare.net(gdm3003) Information Extraction from Web-Scale N-Gram Data gdm3003 Search engines are increasingly relying on structured data to provide direct answers to certain types of queries. However, extracting such structured data from text is challenging, especially due to the scarcity of explicitly expressed knowledge. Even when relying on large document collections, pattern-based information extraction approaches typically expose only insufficient amounts of information. This paper evaluates to what extent n-gram statistics, derived from volumes of texts several orders of magnitude larger than typical corpora, can allow us to overcome this bottleneck. An extensive experimental evaluation is provided for three different binary relations, comparing different sources of n-gram data as well as different learning algorithms. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/informationextractionfromweb-scalen-gramdata-140618124855-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Search engines are increasingly relying on structured data to provide direct answers to certain types of queries. However, extracting such structured data from text is challenging, especially due to the scarcity of explicitly expressed knowledge. Even when relying on large document collections, pattern-based information extraction approaches typically expose only insufficient amounts of information. This paper evaluates to what extent n-gram statistics, derived from volumes of texts several orders of magnitude larger than typical corpora, can allow us to overcome this bottleneck. An extensive experimental evaluation is provided for three different binary relations, comparing different sources of n-gram data as well as different learning algorithms.

Information Extraction from Web-Scale N-Gram Data from Gerard de Melo

]]> 1838 7 https://cdn.slidesharecdn.com/ss_thumbnails/informationextractionfromweb-scalen-gramdata-140618124855-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 UWN: A Large Multilingual Lexical Knowledge Base /slideshow/universal-wordnet/36028032 universalwordnet-140618124319-phpapp01
We present UWN, a large multilingual lexical knowledge base that describes the meanings and relationships of words in over 200 languages. This paper explains how link prediction, information integration and taxonomy induction methods have been used to build UWN based on WordNet and extend it with millions of named entities from Wikipedia. We additionally introduce extensions to cover lexical relationships, frame-semantic knowledge, and language data. An online interface provides human access to the data, while a software API enables applications to look up over 16 million words and names.]]>
We present UWN, a large multilingual lexical knowledge base that describes the meanings and relationships of words in over 200 languages. This paper explains how link prediction, information integration and taxonomy induction methods have been used to build UWN based on WordNet and extend it with millions of named entities from Wikipedia. We additionally introduce extensions to cover lexical relationships, frame-semantic knowledge, and language data. An online interface provides human access to the data, while a software API enables applications to look up over 16 million words and names.]]> Wed, 18 Jun 2014 12:43:19 GMT /slideshow/universal-wordnet/36028032 gdm3003@slideshare.net(gdm3003) UWN: A Large Multilingual Lexical Knowledge Base gdm3003 We present UWN, a large multilingual lexical knowledge base that describes the meanings and relationships of words in over 200 languages. This paper explains how link prediction, information integration and taxonomy induction methods have been used to build UWN based on WordNet and extend it with millions of named entities from Wikipedia. We additionally introduce extensions to cover lexical relationships, frame-semantic knowledge, and language data. An online interface provides human access to the data, while a software API enables applications to look up over 16 million words and names. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/universalwordnet-140618124319-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> We present UWN, a large multilingual lexical knowledge base that describes the meanings and relationships of words in over 200 languages. This paper explains how link prediction, information integration and taxonomy induction methods have been used to build UWN based on WordNet and extend it with millions of named entities from Wikipedia. We additionally introduce extensions to cover lexical relationships, frame-semantic knowledge, and language data. An online interface provides human access to the data, while a software API enables applications to look up over 16 million words and names.

UWN: A Large Multilingual Lexical Knowledge Base from Gerard de Melo

]]> 1091 5 https://cdn.slidesharecdn.com/ss_thumbnails/universalwordnet-140618124319-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Multilingual Text Classification using Ontologies /gdm3003/multilingual-text-classification-using-ontologies multilingualtextclassificationusingontologies-140618123620-phpapp01
In this paper, we investigate strategies for automatically classifying documents in different languages thematically, geographically or according to other criteria. A novel linguistically motivated text representation scheme is presented that can be used with machine learning algorithms in order to learn classifications from pre-classified examples and then automatically classify documents that might be provided in entirely different languages. Our approach makes use of ontologies and lexical resources but goes beyond a simple mapping from terms to concepts by fully exploiting the external knowledge manifested in such resources and mapping to entire regions of concepts. For this, a graph traversal algorithm is used to explore related concepts that might be relevant. Extensive testing has shown that our methods lead to significant improvements compared to existing approaches.]]>
In this paper, we investigate strategies for automatically classifying documents in different languages thematically, geographically or according to other criteria. A novel linguistically motivated text representation scheme is presented that can be used with machine learning algorithms in order to learn classifications from pre-classified examples and then automatically classify documents that might be provided in entirely different languages. Our approach makes use of ontologies and lexical resources but goes beyond a simple mapping from terms to concepts by fully exploiting the external knowledge manifested in such resources and mapping to entire regions of concepts. For this, a graph traversal algorithm is used to explore related concepts that might be relevant. Extensive testing has shown that our methods lead to significant improvements compared to existing approaches.]]> Wed, 18 Jun 2014 12:36:20 GMT /gdm3003/multilingual-text-classification-using-ontologies gdm3003@slideshare.net(gdm3003) Multilingual Text Classification using Ontologies gdm3003 In this paper, we investigate strategies for automatically classifying documents in different languages thematically, geographically or according to other criteria. A novel linguistically motivated text representation scheme is presented that can be used with machine learning algorithms in order to learn classifications from pre-classified examples and then automatically classify documents that might be provided in entirely different languages. Our approach makes use of ontologies and lexical resources but goes beyond a simple mapping from terms to concepts by fully exploiting the external knowledge manifested in such resources and mapping to entire regions of concepts. For this, a graph traversal algorithm is used to explore related concepts that might be relevant. Extensive testing has shown that our methods lead to significant improvements compared to existing approaches. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/multilingualtextclassificationusingontologies-140618123620-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this paper, we investigate strategies for automatically classifying documents in different languages thematically, geographically or according to other criteria. A novel linguistically motivated text representation scheme is presented that can be used with machine learning algorithms in order to learn classifications from pre-classified examples and then automatically classify documents that might be provided in entirely different languages. Our approach makes use of ontologies and lexical resources but goes beyond a simple mapping from terms to concepts by fully exploiting the external knowledge manifested in such resources and mapping to entire regions of concepts. For this, a graph traversal algorithm is used to explore related concepts that might be relevant. Extensive testing has shown that our methods lead to significant improvements compared to existing approaches.

Multilingual Text Classification using Ontologies from Gerard de Melo

]]> 1369 4 https://cdn.slidesharecdn.com/ss_thumbnails/multilingualtextclassificationusingontologies-140618123620-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 Extracting Sense-Disambiguated Example Sentences From Parallel Corpora /slideshow/sense-disambiguatedexamplesentences/36027532 sense-disambiguated-example-sentences-140618123026-phpapp02
Example sentences provide an intuitive means of grasping the meaning of a word, and are frequently used to complement conventional word definitions. When a word has multiple meanings, it is useful to have example sentences for specific senses (and hence definitions) of that word rather than indiscriminately lumping all of them together. In this paper, we investigate to what extent such sense-specific example sentences can be extracted from parallel corpora using lexical knowledge bases for multiple languages as a sense index. We use word sense disambiguation heuristics and a cross-lingual measure of semantic similarity to link example sentences to specific word senses. From the sentences found for a given sense, an algorithm then selects a smaller subset that can be presented to end users, taking into account both representativeness and diversity. Preliminary results show that a precision of around 80% can be obtained for a reasonable number of word senses, and that the subset selection yields convincing results.]]>
Example sentences provide an intuitive means of grasping the meaning of a word, and are frequently used to complement conventional word definitions. When a word has multiple meanings, it is useful to have example sentences for specific senses (and hence definitions) of that word rather than indiscriminately lumping all of them together. In this paper, we investigate to what extent such sense-specific example sentences can be extracted from parallel corpora using lexical knowledge bases for multiple languages as a sense index. We use word sense disambiguation heuristics and a cross-lingual measure of semantic similarity to link example sentences to specific word senses. From the sentences found for a given sense, an algorithm then selects a smaller subset that can be presented to end users, taking into account both representativeness and diversity. Preliminary results show that a precision of around 80% can be obtained for a reasonable number of word senses, and that the subset selection yields convincing results.]]> Wed, 18 Jun 2014 12:30:25 GMT /slideshow/sense-disambiguatedexamplesentences/36027532 gdm3003@slideshare.net(gdm3003) Extracting Sense-Disambiguated Example Sentences From Parallel Corpora gdm3003 Example sentences provide an intuitive means of grasping the meaning of a word, and are frequently used to complement conventional word definitions. When a word has multiple meanings, it is useful to have example sentences for specific senses (and hence definitions) of that word rather than indiscriminately lumping all of them together. In this paper, we investigate to what extent such sense-specific example sentences can be extracted from parallel corpora using lexical knowledge bases for multiple languages as a sense index. We use word sense disambiguation heuristics and a cross-lingual measure of semantic similarity to link example sentences to specific word senses. From the sentences found for a given sense, an algorithm then selects a smaller subset that can be presented to end users, taking into account both representativeness and diversity. Preliminary results show that a precision of around 80% can be obtained for a reasonable number of word senses, and that the subset selection yields convincing results. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/sense-disambiguated-example-sentences-140618123026-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Example sentences provide an intuitive means of grasping the meaning of a word, and are frequently used to complement conventional word definitions. When a word has multiple meanings, it is useful to have example sentences for specific senses (and hence definitions) of that word rather than indiscriminately lumping all of them together. In this paper, we investigate to what extent such sense-specific example sentences can be extracted from parallel corpora using lexical knowledge bases for multiple languages as a sense index. We use word sense disambiguation heuristics and a cross-lingual measure of semantic similarity to link example sentences to specific word senses. From the sentences found for a given sense, an algorithm then selects a smaller subset that can be presented to end users, taking into account both representativeness and diversity. Preliminary results show that a precision of around 80% can be obtained for a reasonable number of word senses, and that the subset selection yields convincing results.

Extracting Sense-Disambiguated Example Sentences From Parallel Corpora from Gerard de Melo

]]> 1704 4 https://cdn.slidesharecdn.com/ss_thumbnails/sense-disambiguated-example-sentences-140618123026-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 Towards a Universal Wordnet by Learning from Combined Evidence /slideshow/cikm2009/36027190 cikm2009-140618122418-phpapp01
Lexical databases are invaluable sources of knowledge about words and their meanings, with numerous applications in areas like NLP, IR, and AI. We propose a methodology for the automatic construction of a large-scale multilingual lexical database where words of many languages are hierarchically organized in terms of their meanings and their semantic relations to other words. This resource is bootstrapped from WordNet, a well-known English-language resource. Our approach extends WordNet with around 1.5 million meaning links for 800,000 words in over 200 languages, drawing on evidence extracted from a variety of resources including existing (monolingual) wordnets, (mostly bilingual) translation dictionaries, and parallel corpora. Graph-based scoring functions and statistical learning techniques are used to iteratively integrate this information and build an output graph. Experiments show that this wordnet has a high level of precision and coverage, and that it can be useful in applied tasks such as cross-lingual text classification.]]>
Lexical databases are invaluable sources of knowledge about words and their meanings, with numerous applications in areas like NLP, IR, and AI. We propose a methodology for the automatic construction of a large-scale multilingual lexical database where words of many languages are hierarchically organized in terms of their meanings and their semantic relations to other words. This resource is bootstrapped from WordNet, a well-known English-language resource. Our approach extends WordNet with around 1.5 million meaning links for 800,000 words in over 200 languages, drawing on evidence extracted from a variety of resources including existing (monolingual) wordnets, (mostly bilingual) translation dictionaries, and parallel corpora. Graph-based scoring functions and statistical learning techniques are used to iteratively integrate this information and build an output graph. Experiments show that this wordnet has a high level of precision and coverage, and that it can be useful in applied tasks such as cross-lingual text classification.]]> Wed, 18 Jun 2014 12:24:18 GMT /slideshow/cikm2009/36027190 gdm3003@slideshare.net(gdm3003) Towards a Universal Wordnet by Learning from Combined Evidence gdm3003 Lexical databases are invaluable sources of knowledge about words and their meanings, with numerous applications in areas like NLP, IR, and AI. We propose a methodology for the automatic construction of a large-scale multilingual lexical database where words of many languages are hierarchically organized in terms of their meanings and their semantic relations to other words. This resource is bootstrapped from WordNet, a well-known English-language resource. Our approach extends WordNet with around 1.5 million meaning links for 800,000 words in over 200 languages, drawing on evidence extracted from a variety of resources including existing (monolingual) wordnets, (mostly bilingual) translation dictionaries, and parallel corpora. Graph-based scoring functions and statistical learning techniques are used to iteratively integrate this information and build an output graph. Experiments show that this wordnet has a high level of precision and coverage, and that it can be useful in applied tasks such as cross-lingual text classification. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cikm2009-140618122418-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lexical databases are invaluable sources of knowledge about words and their meanings, with numerous applications in areas like NLP, IR, and AI. We propose a methodology for the automatic construction of a large-scale multilingual lexical database where words of many languages are hierarchically organized in terms of their meanings and their semantic relations to other words. This resource is bootstrapped from WordNet, a well-known English-language resource. Our approach extends WordNet with around 1.5 million meaning links for 800,000 words in over 200 languages, drawing on evidence extracted from a variety of resources including existing (monolingual) wordnets, (mostly bilingual) translation dictionaries, and parallel corpora. Graph-based scoring functions and statistical learning techniques are used to iteratively integrate this information and build an output graph. Experiments show that this wordnet has a high level of precision and coverage, and that it can be useful in applied tasks such as cross-lingual text classification.

Towards a Universal Wordnet by Learning from Combined Evidence from Gerard de Melo

]]> 1851 5 https://cdn.slidesharecdn.com/ss_thumbnails/cikm2009-140618122418-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 Not Quite the Same: Identity Constraints for the Web of Linked Data /slideshow/not-quite-the-same-identity-constraints-for-the-web-of-linked-data/32217313 slides-140312054523-phpapp02
Linked Data is based on the idea that information from different sources can flexibly be connected to enable novel applications that individual datasets do not support on their own. This hinges upon the existence of links between datasets that would otherwise be isolated. The most notable form, sameAs links, are intended to express that two identifiers are equivalent in all respects. Unfortunately, many existing ones do not reflect such genuine identity. This study provides a novel method to analyse this phenomenon, based on a thorough theoretical analysis, as well as a novel graph-based method to resolve such issues to some extent. Our experiments on a representative Web-scale set of sameAs links from the Web of Data show that our method can identify and remove hundreds of thousands of constraint violations.]]>
Linked Data is based on the idea that information from different sources can flexibly be connected to enable novel applications that individual datasets do not support on their own. This hinges upon the existence of links between datasets that would otherwise be isolated. The most notable form, sameAs links, are intended to express that two identifiers are equivalent in all respects. Unfortunately, many existing ones do not reflect such genuine identity. This study provides a novel method to analyse this phenomenon, based on a thorough theoretical analysis, as well as a novel graph-based method to resolve such issues to some extent. Our experiments on a representative Web-scale set of sameAs links from the Web of Data show that our method can identify and remove hundreds of thousands of constraint violations.]]> Wed, 12 Mar 2014 05:45:23 GMT /slideshow/not-quite-the-same-identity-constraints-for-the-web-of-linked-data/32217313 gdm3003@slideshare.net(gdm3003) Not Quite the Same: Identity Constraints for the Web of Linked Data gdm3003 Linked Data is based on the idea that information from different sources can flexibly be connected to enable novel applications that individual datasets do not support on their own. This hinges upon the existence of links between datasets that would otherwise be isolated. The most notable form, sameAs links, are intended to express that two identifiers are equivalent in all respects. Unfortunately, many existing ones do not reflect such genuine identity. This study provides a novel method to analyse this phenomenon, based on a thorough theoretical analysis, as well as a novel graph-based method to resolve such issues to some extent. Our experiments on a representative Web-scale set of sameAs links from the Web of Data show that our method can identify and remove hundreds of thousands of constraint violations. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/slides-140312054523-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Linked Data is based on the idea that information from different sources can flexibly be connected to enable novel applications that individual datasets do not support on their own. This hinges upon the existence of links between datasets that would otherwise be isolated. The most notable form, sameAs links, are intended to express that two identifiers are equivalent in all respects. Unfortunately, many existing ones do not reflect such genuine identity. This study provides a novel method to analyse this phenomenon, based on a thorough theoretical analysis, as well as a novel graph-based method to resolve such issues to some extent. Our experiments on a representative Web-scale set of sameAs links from the Web of Data show that our method can identify and remove hundreds of thousands of constraint violations.

Not Quite the Same: Identity Constraints for the Web of Linked Data from Gerard de Melo

]]> 989 2 https://cdn.slidesharecdn.com/ss_thumbnails/slides-140312054523-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 Good, Great, Excellent: Global Inference of Semantic Intensities /slideshow/good-great-excellent-global-inference-of-semantic-intensities/32216257 lexical-intensities-140312051727-phpapp02
Adjectives like good, great, and excellent are similar in meaning, but differ in intensity. Intensity order information is very useful for language learners as well as in several NLP tasks, but is missing in most lexical resources (dictionaries, WordNet, and thesauri). In this paper, we present a primarily unsupervised approach that uses semantics from Web-scale data (e.g., phrases like good but not excellent) to rank words by assigning them positions on a continuous scale. We rely on Mixed Integer Linear Programming to jointly determine the ranks, such that individual decisions benefit from global information. When ranking English adjectives, our global algorithm achieves substantial improvements over previous work on both pairwise and rank correlation metrics (specifically, 70% pairwise accuracy as compared to only 56% by previous work). Moreover, our approach can incorporate external synonymy information (increasing its pairwise accuracy to 78%) and extends easily to new languages. ]]>
Adjectives like good, great, and excellent are similar in meaning, but differ in intensity. Intensity order information is very useful for language learners as well as in several NLP tasks, but is missing in most lexical resources (dictionaries, WordNet, and thesauri). In this paper, we present a primarily unsupervised approach that uses semantics from Web-scale data (e.g., phrases like good but not excellent) to rank words by assigning them positions on a continuous scale. We rely on Mixed Integer Linear Programming to jointly determine the ranks, such that individual decisions benefit from global information. When ranking English adjectives, our global algorithm achieves substantial improvements over previous work on both pairwise and rank correlation metrics (specifically, 70% pairwise accuracy as compared to only 56% by previous work). Moreover, our approach can incorporate external synonymy information (increasing its pairwise accuracy to 78%) and extends easily to new languages. ]]> Wed, 12 Mar 2014 05:17:27 GMT /slideshow/good-great-excellent-global-inference-of-semantic-intensities/32216257 gdm3003@slideshare.net(gdm3003) Good, Great, Excellent: Global Inference of Semantic Intensities gdm3003 Adjectives like good, great, and excellent are similar in meaning, but differ in intensity. Intensity order information is very useful for language learners as well as in several NLP tasks, but is missing in most lexical resources (dictionaries, WordNet, and thesauri). In this paper, we present a primarily unsupervised approach that uses semantics from Web-scale data (e.g., phrases like good but not excellent) to rank words by assigning them positions on a continuous scale. We rely on Mixed Integer Linear Programming to jointly determine the ranks, such that individual decisions benefit from global information. When ranking English adjectives, our global algorithm achieves substantial improvements over previous work on both pairwise and rank correlation metrics (specifically, 70% pairwise accuracy as compared to only 56% by previous work). Moreover, our approach can incorporate external synonymy information (increasing its pairwise accuracy to 78%) and extends easily to new languages. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lexical-intensities-140312051727-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Adjectives like good, great, and excellent are similar in meaning, but differ in intensity. Intensity order information is very useful for language learners as well as in several NLP tasks, but is missing in most lexical resources (dictionaries, WordNet, and thesauri). In this paper, we present a primarily unsupervised approach that uses semantics from Web-scale data (e.g., phrases like good but not excellent) to rank words by assigning them positions on a continuous scale. We rely on Mixed Integer Linear Programming to jointly determine the ranks, such that individual decisions benefit from global information. When ranking English adjectives, our global algorithm achieves substantial improvements over previous work on both pairwise and rank correlation metrics (specifically, 70% pairwise accuracy as compared to only 56% by previous work). Moreover, our approach can incorporate external synonymy information (increasing its pairwise accuracy to 78%) and extends easily to new languages.

Good, Great, Excellent: Global Inference of Semantic Intensities from Gerard de Melo

]]> 2007 5 https://cdn.slidesharecdn.com/ss_thumbnails/lexical-intensities-140312051727-phpapp02-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 YAGO-SUMO: Integrating YAGO into the Suggested Upper Merged Ontology /slideshow/presentation-22679220/22679220 presentation-130608223128-phpapp01
The YAGO-SUMO integration incorporates millions of entities from YAGO, which is based on Wikipedia and WordNet, into the Suggested Upper Merged Ontology (SUMO), a highly axiomatized formal upper ontology. With the combined force of the two ontologies, an enormous, unprecedented corpus of formalized world knowledge is available for automated processing and reasoning, providing information about millions of entities such as people, cities, organizations, and companies. Compared to the original YAGO, more advanced reasoning is possible due to the axiomatic knowledge delivered by SUMO. A reasoner can conclude e.g. that a child of a human must also be a human and cannot be born before its parents, or that two people sharing the same parents must be siblings.]]>
The YAGO-SUMO integration incorporates millions of entities from YAGO, which is based on Wikipedia and WordNet, into the Suggested Upper Merged Ontology (SUMO), a highly axiomatized formal upper ontology. With the combined force of the two ontologies, an enormous, unprecedented corpus of formalized world knowledge is available for automated processing and reasoning, providing information about millions of entities such as people, cities, organizations, and companies. Compared to the original YAGO, more advanced reasoning is possible due to the axiomatic knowledge delivered by SUMO. A reasoner can conclude e.g. that a child of a human must also be a human and cannot be born before its parents, or that two people sharing the same parents must be siblings.]]> Sat, 08 Jun 2013 22:31:28 GMT /slideshow/presentation-22679220/22679220 gdm3003@slideshare.net(gdm3003) YAGO-SUMO: Integrating YAGO into the Suggested Upper Merged Ontology gdm3003 The YAGO-SUMO integration incorporates millions of entities from YAGO, which is based on Wikipedia and WordNet, into the Suggested Upper Merged Ontology (SUMO), a highly axiomatized formal upper ontology. With the combined force of the two ontologies, an enormous, unprecedented corpus of formalized world knowledge is available for automated processing and reasoning, providing information about millions of entities such as people, cities, organizations, and companies. Compared to the original YAGO, more advanced reasoning is possible due to the axiomatic knowledge delivered by SUMO. A reasoner can conclude e.g. that a child of a human must also be a human and cannot be born before its parents, or that two people sharing the same parents must be siblings. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/presentation-130608223128-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> The YAGO-SUMO integration incorporates millions of entities from YAGO, which is based on Wikipedia and WordNet, into the Suggested Upper Merged Ontology (SUMO), a highly axiomatized formal upper ontology. With the combined force of the two ontologies, an enormous, unprecedented corpus of formalized world knowledge is available for automated processing and reasoning, providing information about millions of entities such as people, cities, organizations, and companies. Compared to the original YAGO, more advanced reasoning is possible due to the axiomatic knowledge delivered by SUMO. A reasoner can conclude e.g. that a child of a human must also be a human and cannot be born before its parents, or that two people sharing the same parents must be siblings.

YAGO-SUMO: Integrating YAGO into the Suggested Upper Merged Ontology from Gerard de Melo

]]> 2239 5 https://cdn.slidesharecdn.com/ss_thumbnails/presentation-130608223128-phpapp01-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 https://cdn.slidesharecdn.com/profile-photo-gdm3003-48x48.jpg?cb=1644348019 gerard.demelo.org/ https://cdn.slidesharecdn.com/ss_thumbnails/slides-export-181011205847-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/semac-graph-node-embeddings-for-link-prediction/119148104 SEMAC Graph Node Embed... https://cdn.slidesharecdn.com/ss_thumbnails/how-to-manage-your-research-160328114041-thumbnail.jpg?width=320&height=320&fit=bounds gdm3003/how-to-manage-your-research How to Manage your Res... https://cdn.slidesharecdn.com/ss_thumbnails/knowlywood-mining-activity-knowledge-from-hollywood-narratives-151126065134-lva1-app6891-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/knowlywood-mining-activity-knowledge-from-hollywood-narratives/55533408 Knowlywood: Mining Act...