Filters








13 Hits in 1.6 sec

Relational Graph Convolutional Networks: A Closer Look [article]

Thiviyan Thanapalasingam, Lucas van Berkel, Peter Bloem, Paul Groth
2021 arXiv   pre-print
In this paper, we describe a reproduction of the Relational Graph Convolutional Network (RGCN). Using our reproduction, we explain the intuition behind the model. Our reproduction results empirically validate the correctness of our implementations using benchmark Knowledge Graph datasets on node classification and link prediction tasks. Our explanation provides a friendly understanding of the different components of the RGCN for both users and researchers extending the RGCN approach.
more » ... , we introduce two new configurations of the RGCN that are more parameter efficient. The code and datasets are available at https://github.com/thiviyanT/torch-rgcn.
arXiv:2107.10015v1 fatcat:n6aaycppd5difaytay2liedbqm

Supporting Springer Nature Editors by means of Semantic Technologies

Francesco Osborne, Angelo Antonio Salatino, Aliaksandr Birukou, Thiviyan Thanapalasingam, Enrico Motta
2017 International Semantic Web Conference  
The Open University and Springer Nature have been collaborating since 2015 in the development of an array of semantically-enhanced solutions supporting editors in i) classifying proceedings and other editorial products with respect to the relevant research areas and ii) taking informed decisions about their marketing strategy. These solutions include i) the Smart Topic API, which automatically maps keywords associated with published papers to semantically characterized topics, which are drawn
more » ... om a very large and automatically-generated ontology of Computer Science topics; ii) the Smart Topic Miner, which helps editors to associate scholarly metadata to books; and iii) the Smart Book Recommender, which assists editors in deciding which editorial products should be marketed in a specific venue.
dblp:conf/semweb/OsborneSBTM17 fatcat:crnzhcnocrcbth24tgcyi4vlhe

Ontology-Based Recommendation of Editorial Products [chapter]

Thiviyan Thanapalasingam, Francesco Osborne, Aliaksandr Birukou, Enrico Motta
2018 Lecture Notes in Computer Science  
Major academic publishers need to be able to analyse their vast catalogue of products and select the best items to be marketed in scientific venues. This is a complex exercise that requires characterising with a high precision the topics of thousands of books and matching them with the interests of the relevant communities. In Springer Nature, this task has been traditionally handled manually by publishing editors. However, the rapid growth in the number of scientific publications and the
more » ... c nature of the Computer Science landscape has made this solution increasingly inefficient. We have addressed this issue by creating Smart Book Recommender (SBR), an ontology-based recommender system developed by The Open University (OU) in collaboration with Springer Nature, which supports their Computer Science editorial team in selecting the products to market at specific venues. SBR recommends books, journals, and conference proceedings relevant to a conference by taking advantage of a semantically enhanced representation of about 27K editorial products. This is based on the Computer Science Ontology, a very large-scale, automatically generated taxonomy of research areas. SBR also allows users to investigate why a certain publication was suggested by the system. It does so by means of an interactive graph view that displays the topic taxonomy of the recommended editorial product and compares it with the topic-centric characterization of the input conference. An evaluation carried out with seven Springer Nature editors and seven OU researchers has confirmed the effectiveness of the solution.
doi:10.1007/978-3-030-00668-6_21 fatcat:nfqfdnxnojcy7a5ovysp57fpni

Classifying Research Papers with the Computer Science Ontology

Angelo Antonio Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Francesco Osborne, Enrico Motta
2018 International Semantic Web Conference  
Ontologies of research areas are important tools for characterising, exploring and analysing the research landscape. We recently released the Computer Science Ontology (CSO), a large-scale, automatically generated ontology of research areas, which includes about 26K topics and 226K semantic relationships. CSO currently powers several tools adopted by the Springer Nature editorial team and has been used to enable a variety of solutions, such as classifying research publications, detecting
more » ... h communities, and predicting research trends. As an effort to encourage the usage of CSO, we have developed the CSO Portal, a web application that enables users to download, explore, and provide granular feedbacks at different levels of the ontology. In this paper, we present the CSO Classifier, an application for automatically classifying academic papers according to the rich taxonomy of topics from CSO. The aim is to facilitate the adoption of CSO across the various communities engaged with scholarly data and to foster the development of new applications based on this knowledge base.
dblp:conf/semweb/SalatinoTMOM18a fatcat:uacfcl4ejvehldfpcyphg6iv2m

The Smart Book Recommender: An Ontology-Driven Application for Recommending Editorial Products

Thiviyan Thanapalasingam, Francesco Osborne, Aliaksandr Birukou, Enrico Motta
2018 International Semantic Web Conference  
Promoting books and journals to the relevant research communities is an important task for major academic publishers. Unfortunately, identifying which are the best editorial products to market at a certain academic venue is a time-consuming and error-prone process. Here we present the Smart Book Recommender (SBR), an ontology-based recommender that supports the Springer Nature editorial team in selecting the editorial products to market at specific venues. SBR provides an interactive
more » ... on for analysing the topics characterizing conference series and books. It builds on a dataset of 27K books, journals, and conference proceedings annotated with topics from the Computer Science Ontology, a large-scale ontology of research areas. A user study showed that SBR is able to produce useful recommendations for both editors and researchers.
dblp:conf/semweb/Thanapalasingam18a fatcat:kqewwnn7xfgdvf4t7a4gw7lxci

Prompting as Probing: Using Language Models for Knowledge Base Construction [article]

Dimitrios Alivanistos, Selene Báez Santamaría, Michael Cochez, Jan-Christoph Kalo, Emile van Krieken, Thiviyan Thanapalasingam
2022 arXiv   pre-print
Language Models (LMs) have proven to be useful in various downstream applications, such as summarisation, translation, question answering and text classification. LMs are becoming increasingly important tools in Artificial Intelligence, because of the vast quantity of information they can store. In this work, we present ProP (Prompting as Probing), which utilizes GPT-3, a large Language Model originally proposed by OpenAI in 2020, to perform the task of Knowledge Base Construction (KBC). ProP
more » ... plements a multi-step approach that combines a variety of prompting techniques to achieve this. Our results show that manual prompt curation is essential, that the LM must be encouraged to give answer sets of variable lengths, in particular including empty answer sets, that true/false questions are a useful device to increase precision on suggestions generated by the LM, that the size of the LM is a crucial factor, and that a dictionary of entity aliases improves the LM score. Our evaluation study indicates that these proposed techniques can substantially enhance the quality of the final predictions: ProP won track 2 of the LM-KBC competition, outperforming the baseline by 36.4 percentage points. Our implementation is available on https://github.com/HEmile/iswc-challenge.
arXiv:2208.11057v2 fatcat:jna2nnrbhvgitaah44hiskped4

The Computer Science Ontology: A Large-Scale Taxonomy of Research Areas [chapter]

Angelo A. Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Francesco Osborne, Enrico Motta
2018 Lecture Notes in Computer Science  
Ontologies of research areas are important tools for characterising, exploring, and analysing the research landscape. Some fields of research are comprehensively described by large-scale taxonomies, e.g., MeSH in Biology and PhySH in Physics. Conversely, current Computer Science taxonomies are coarse-grained and tend to evolve slowly. For instance, the ACM classification scheme contains only about 2K research topics and the last version dates back to 2012. In this paper, we introduce the
more » ... r Science Ontology (CSO), a largescale, automatically generated ontology of research areas, which includes about 26K topics and 226K semantic relationships. It was created by applying the Klink-2 algorithm on a very large dataset of 16M scientific articles. CSO presents two main advantages over the alternatives: i) it includes a very large number of topics that do not appear in other classifications, and ii) it can be updated automatically by running Klink-2 on recent corpora of publications. CSO powers several tools adopted by the editorial team at Springer Nature and has been used to enable a variety of solutions, such as classifying research publications, detecting research communities, and predicting research trends. To facilitate the uptake of CSO we have developed the CSO Portal, a web application that enables users to download, explore, and provide granular feedback on CSO at different levels. Users can use the portal to rate topics and relationships, suggest missing relationships, and visualise sections of the ontology. The portal will support the publication of and access to regular new releases of CSO, with the aim of providing a comprehensive resource to the various communities engaged with scholarly data.
doi:10.1007/978-3-030-00668-6_12 fatcat:c3arhzreivd57hi462ibpztktu

Smart Book Recommender: A Semantic Recommendation Engine for Editorial Products

Francesco Osborne, Thiviyan Thanapalasingam, Angelo Antonio Salatino, Aliaksandr Birukou, Enrico Motta
2017 International Semantic Web Conference  
Academic publishers, such as Springer Nature, need to constantly make informed decisions about how and where to market their editorial products. In the field of Computer Science (CS), it is particularly critical to assess which books will be of interest to the attendees of a conference. Typically, these items are manually chosen by publishing editors, on the basis of their personal experience. To make this process both faster and more robust we have developed the Smart Book Recommender (SBR), a
more » ... semantic application designed to support the Springer Nature editorial team in promoting their publications at CS venues. SBR takes as input the proceedings of a conference and suggests books, journals, and other conference proceedings which are likely to be relevant to the attendees of the conference in question. It does so by taking advantage of a semantic representation of topics, which builds on a very large ontology of Computer Science topics; characterizing Springer Nature books as distributions of semantic topics; and approaching the problem as one of semantic matching between such distributions of semantic topics.
dblp:conf/semweb/OsborneTSBM17 fatcat:u6uzfhhz6zhwjbktaozqrqjbme

The Computer Science Ontology: A Comprehensive Automatically-Generated Taxonomy of Research Areas

Angelo A. Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Aliaksandr Birukou, Francesco Osborne, Enrico Motta
2019 Data Intelligence  
Thanapalasingam (thiviyan.thanapalasingam@open. ac.uk) designed and developed the resource, wrote the paper, and reviewed drafts of the paper. A.  ...  ORCID: 0000-0002-4763-3943 Thiviyan Thanapalasingam is a PhD candidate at the University of Amsterdam, The Netherlands.  ...  Under the supervision of Professor Paul Groth, Thiviyan is studying graph embedding methods for rapidly constructing Knowledge Graphs for the natural sciences and adapting them for downstream applications  ... 
doi:10.1162/dint_a_00055 fatcat:o6xh6hqyrjgchmjkvruu4s4hbi

The CSO Classifier: Ontology-Driven Detection of Research Topics in Scholarly Articles [chapter]

Angelo A. Salatino, Francesco Osborne, Thiviyan Thanapalasingam, Enrico Motta
2019 Lecture Notes in Computer Science  
Classifying research papers according to their research topics is an important task to improve their retrievability, assist the creation of smart analytics, and support a variety of approaches for analysing and making sense of the research environment. In this paper, we present the CSO Classifier, a new unsupervised approach for automatically classifying research papers according to the Computer Science Ontology (CSO), a comprehensive ontology of re-search areas in the field of Computer
more » ... The CSO Classifier takes as input the metadata associated with a research paper (title, abstract, keywords) and returns a selection of research concepts drawn from the ontology. The approach was evaluated on a gold standard of manually annotated articles yielding a significant improvement over alternative methods.
doi:10.1007/978-3-030-30760-8_26 fatcat:dc4wa4rrrfgvtatlunnb2jirue

Linked Open Data Validity -- A Technical Report from ISWS 2018 [article]

Tayeb Abderrahmani Ghor, Esha Agrawal, Mehwish Alam, Omar Alqawasmeh, Claudia D'amato, Amina Annane, Amr Azzam, Andrew Berezovskyi, Russa Biswas, Mathias Bonduel, Quentin Brabant, Cristina-iulia Bucur, Elena Camossi, Valentina Anita Carriero, Shruthi Chari (+48 others)
2019 arXiv   pre-print
Linked Open Data (LOD) is the publicly available RDF data in the Web. Each LOD entity is identfied by a URI and accessible via HTTP. LOD encodes globalscale knowledge potentially available to any human as well as artificial intelligence that may want to benefit from it as background knowledge for supporting their tasks. LOD has emerged as the backbone of applications in diverse fields such as Natural Language Processing, Information Retrieval, Computer Vision, Speech Recognition, and many more.
more » ... Nevertheless, regardless of the specific tasks that LOD-based tools aim to address, the reuse of such knowledge may be challenging for diverse reasons, e.g. semantic heterogeneity, provenance, and data quality. As aptly stated by Heath et al. Linked Data might be outdated, imprecise, or simply wrong": there arouses a necessity to investigate the problem of linked data validity. This work reports a collaborative effort performed by nine teams of students, guided by an equal number of senior researchers, attending the International Semantic Web Research School (ISWS 2018) towards addressing such investigation from different perspectives coupled with different approaches to tackle the issue.
arXiv:1903.12554v1 fatcat:e25yvjsucvghzol4uo3omflh7i

Early Detection of Research Trends [article]

Angelo Antonio Salatino
2019 arXiv   pre-print
Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Francesco Osborne, Enrico Motta. "Classifying Research Papers with the Computer Science Ontology".  ...  Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Francesco Osborne, Enrico Motta. "The Computer Science Ontology: A Large-Scale Taxonomy of Research Areas."  ... 
arXiv:1912.08928v1 fatcat:semryxqrtjgzpet7ijbrokmsh4

Early Detection of Research Trends

Angelo Salatino
2019
Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Francesco Osborne, Enrico Motta. "Classifying Research Papers with the Computer Science Ontology".  ...  Salatino, Thiviyan Thanapalasingam, Andrea Mannocci, Francesco Osborne, Enrico Motta. "The Computer Science Ontology: A Large-Scale Taxonomy of Research Areas."  ... 
doi:10.21954/ou.ro.00010698 fatcat:fyb2dip2xfbqlmvmvqnb5hbr7i