299 research outputs found
Entity Typing Datasets
No full textThese are the datasets used in the Entity Type Prediction task for Knowledge Graph Completion.
DB630k_Fine-grained_Hierarchical.zip dataset has been used in the papers [1] and [2]. It is an extended version of DBpedia630k dataset originally created for Text classification and is available here.
FIGER.zip dataset has also been used in the papers [1] and [2].
MultilingualETdata.zip dataset has been used in the paper [3]
NamesETdata.zip dataset has been used in the paper [4]. The CaLiGraph test dataset can also be downloaded here.
[1] Biswas R, Sofronova R, Sack H, Alam M. Cat2type: Wikipedia category embeddings for entity typing in knowledge graphs. InProceedings of the 11th on Knowledge Capture Conference 2021 Dec 2 (pp. 81-88).
[2] Biswas R, Portisch J, Paulheim H, Sack H, Alam M. Entity type prediction leveraging graph walks and entity descriptions. In The Semantic Web–ISWC 2022: 21st International Semantic Web Conference, Virtual Event, October 23–27, 2022, Proceedings 2022 Oct 16 (pp. 392-410). Cham: Springer International Publishing.
[3] Biswas R, Chen Y, Paulheim H, Sack H, Alam M. It’s All in the Name: Entity Typing Using Multilingual Language Models. In The Semantic Web: ESWC 2022 Satellite Events: Hersonissos, Crete, Greece, May 29–June 2, 2022, Proceedings 2022 Jul 20 (pp. 36-41). Cham: Springer International Publishing.
[4] Biswas R, Sofronova R, Alam M, Heist N, Paulheim H, Sack H. Do judge an entity by its name! entity typing using language models. In The Semantic Web: ESWC 2021 Satellite Events: Virtual Event, June 6–10, 2021, Revised Selected Papers 18 2021 (pp. 65-70). Springer International Publishing
Cucina russa e lessico italiano. Il caso di 'Insalata russa'
No full textIn the present article the author deals with the culinary metaphor ‘insalata russa’ (‘Russian salad’) in Italian language and culture. The author starts with a short review of the dish that is called in Italian ‘insalata russa’, and that roughly corresponds to the Russian salad ‘Olivier’. As to the uses of the culinary metaphor ‘insalata russa’, analyzed by the author, they point to the fact that in Italian it is used with the meaning of ‘mix of heterogeneous and varied elements’. The use occurrences of the locution ‘insalata russa’ comprise the titles of three anthologies of tales (published respectively in 1925, 1934 and 1996), the Italian title of the Russian film Okno v Pariž (Window to Paris), 1994, and the results of the query ‘insalata russa’ in the corpora of Italian language COris/ COdis. Finally, the author compares these results with those provided by the search of the same locution in Russian (‘русский салат’). This last search reveals that in Russian the locution ‘Russian salad’ is used exclusively in its literal sense
HierClasSArt: Knowledge-Aware Hierarchical Classification of Scholarly Articles
Get PDFA huge number of scholarly articles published every day in different domains makes it hard for the experts to organize and stay updated with the new research in a particular domain. This study gives an overview of a new approach, HierClasSArt, for knowledge aware hierarchical classification of the scholarly articles for mathematics into a predefined taxonomy. The method uses combination of neural networks and Knowledge Graphs for better document representation along with the meta-data information. This position paper further discusses the open problems about incorporation of new articles and evolving hierarchies in the pipeline. Mathematics domain has been used as a use-case
Multilingual Knowledge Graphs and Low-Resource Languages: A Review
Get PDFThere is a lack of multilingual data to support applications in a large number of languages, especially for low-resource languages. Knowledge graphs (KG) could contribute to closing the gap of language support by providing easily accessible, machine-readable, multilingual linked data, which can be reused across applications. In this paper, we provide an overview of work in the domain of multilingual KGs with a focus on low-resource languages. We review the current state of multilingual KGs along with the different aspects that are crucial for creating KGs with language coverage in mind. Special consideration is given to challenges particular to low-resource languages in KGs. We further provide an overview of applications that yield multilingual KG information as well as downstream applications reusing such multilingual data. Finally, we explore open problems regarding multilingual KGs with a focus on low-resource languages
Image2Type: Entity Type Prediction via Image Analysis
Get PDFEntity type prediction is the task to assign an entity in a Knowledge Graph (KG) its semantic type. However, the type information in most open KGs such as DBpedia or Wikidata are incomplete and noisy. Thereby the type of an entity is a fundamental information.
Currently, most state-of-the-art entity type prediction models use only structured data to perform entity type prediction. This reduces prediction accuracy, creates incomplete and noisy type information. At the same time 51.1% of entities in the data set
DBpedia630k have at least one associated image. Hence it is obvious to extract the additional information incorporated in these images to improve accuracy of entity type prediction to complete type information. This thesis presents an approach which creates
a combined entity representation consisting of image features and structural information.
On top of it a fully connected neural network is deployed for classification. The model performance is measured on two newly created real-world benchmark datasets. The results suggest that the approach is suitable to perform entity type prediction, however optimization is needed to improve performance
Embedding based Link Prediction for Knowledge Graph Completion
Get PDFThis thesis proposes a novel Knowledge Graph (KG) embedding model for Link Prediction (LP) for Knowledge Graph Completion (KGC). The missing links in a KG are predicted based on the
existing contextual information as well as textual entity descriptions.
The model outperforms the state-of-the-art (SOTA) model DKRL for
FB15k and FB15k-237 datasets
Embedding Based Link Prediction for Knowledge Graph Completion
Get PDFKnowledge Graphs (KGs) are the most widely used representation of structured information about a particular domain consisting of billions of facts in the form of entities (nodes) and relations (edges) between them. Besides, the KGs also encapsulate the semantic type information of the entities. The last two decades have witnessed a constant growth of KGs in various domains such as government, scholarly data, biomedical domains, etc. KGs have been used in Machine Learning based applications such as entity linking, question answering, recommender systems, etc. Open KGs are mostly heuristically created, automatically generated from heterogeneous resources such as text, images, etc., or are human-curated. However, these KGs are often incomplete, i.e., there are missing links between the entities and missing links between the entities and their corresponding entity types. This thesis focuses on addressing these two challenges of link prediction for Knowledge Graph Completion (KGC):
\textbf{(i)} General Link Prediction in KGs that include head and tail prediction, triple classification, and
\textbf{(ii)} Entity Type Prediction.
Most of the graph mining algorithms are proven to be of high complexity, deterring their usage in KG-based applications. In recent years, KG embeddings have been trained to represent the entities and relations in the KG in a low-dimensional vector space preserving the graph structure. In most published works such as the translational models, convolutional models, semantic matching, etc., the triple information is used to generate the latent representation of the entities and relations.
In this dissertation, it is argued that contextual information about the entities obtained from the random walks, and textual entity descriptions, are the keys to improving the latent representation of the entities for KGC. The experimental results show that the knowledge obtained from the context of the entities supports the hypothesis. Several methods have been proposed for KGC and their effectiveness is shown empirically in this thesis. Firstly, a novel multi-hop attentive KG embedding model MADLINK is proposed for Link Prediction. It considers the contextual information of the entities by using random walks as well as textual entity descriptions of the entities. Secondly, a novel architecture exploiting the information contained in a pre-trained contextual Neural Language Model (NLM) is proposed for Triple Classification. Thirdly, the limitations of the current state-of-the-art (SoTA) entity type prediction models have been analysed and a novel entity typing model CAT2Type is proposed that exploits the Wikipedia Categories which is one of the most under-treated features of the KGs. This model can also be used to predict missing types of unseen entities i.e., the newly added entities in the KG.
Finally, another novel architecture GRAND is proposed to predict the missing entity types in KGs using multi-label, multi-class, and hierarchical classification by leveraging different strategic graph walks in the KGs. The extensive experiments and ablation studies show that all the proposed models outperform the current SoTA models and set new baselines for KGC.
The proposed models establish that the NLMs and the contextual information of the entities in the KGs together with the different neural network architectures benefit KGC. The promising results and observations open up interesting scopes for future research involving exploiting the proposed models in domain-specific KGs such as scholarly data, biomedical data, etc. Furthermore, the link prediction model can be exploited as a base model for the entity alignment task as it considers the neighbourhood information of the entities
A VIRADA RUSSA PARA A AMÉRICA LATINA
Get PDFThis paper describes the current relations of Russia with main Latin American countries: Brazil, Argentina, Venezuela and Cuba in the commercial, economical and military scope. The author calls the attention to the real intentions of Russia’s approximation policy with the continent: would the geopolitics partners be allies in recuperate the Russian status of directed power against the United States, or just a smart play due to the emergence of new powers in this multi-polar world?O artigo descreve as atuais relações da Rússia com os principais países latino-americanos: Brasil, Argentina, Venezuela e Cuba no âmbito comercial, econômico e militar. O autor chama atenção para as verdadeiras intenções da política russa de aproximação com o continente: seriam as parcerias geopolíticas aliadas na recuperação do status russo de potência direcionada contra os Estados Unidos ou simplesmente uma jogada inteligente frente à emergência de novas potências no mundo multipolar
SOBRE INDEXAÇÃO DE DINHEIRO CONCEDIDO POR DECISÃO JUDICIAL NA FEDERAÇÃO RUSSA
Get PDFThrough three resolutions adopted in 2018 and 2021, the Constitutional Court of the Russian Federation «revived» the indexation institution of funds collected by a court decision, recognizing Articles 208 of the Civil Procedure Code of the Russian Federation and Articles 183 of the Arbitration Procedure Code of the Russian Federation as inconsistent with the Constitution of the Russian Federation. The author of the study shows that the reproaches of the body of constitutional justice against the articles of procedural codes are unfounded. Indexation is an institution of substantive, not procedural law, and the application of the rules of procedural law without taking into account the results of the creditor's application of substantive legal methods of protection entails unjust enrichment and is unacceptable. «Money collected by the court» is a generic concept, their indexation without taking into account the economic content of these funds and the legal nature of the requirements, as a result of which they were awarded, is impossible.Através de três resoluções adoptadas em 2018 e 2021, o Tribunal Constitucional da Federação Russa "ressuscitou" a instituição de indexação dos fundos recolhidos por decisão judicial, reconhecendo os artigos 208º do Código de Processo Civil da Federação Russa e os artigos 183º do Código de Processo Arbitral da Federação Russa como inconsistentes com a Constituição da Federação Russa. O autor do estudo mostra que as acusações do órgão de justiça constitucional contra os artigos dos códigos de processo são infundadas. A indexação é uma instituição de direito substantivo e não processual, e a aplicação das regras do direito processual sem ter em conta os resultados da aplicação pelo credor de métodos legais substantivos de proteção implica um enriquecimento injusto e é inaceitável. O "dinheiro cobrado pelo tribunal" é um conceito genérico, a sua indexação sem ter em conta o conteúdo económico destes fundos e a natureza jurídica dos requisitos, em resultado dos quais foram concedidos, é impossível
Nuovi orientamenti e strumenti metodologici nella linguistica russa
No full textSi ricostruisce l’evoluzione della linguistica russa nei primi quindici anni dopo la perestrojka e si evidenziano le innovazioni sia dal punto di vista delle concezioni teoriche, sia dei metodi e degli strumenti di analisi.The authors focuse on the recent evolution of Russian Language which has been challenging theoretical as well as applied Russian Linguistics over the last two decades . The most important schools and authors of contemporary Russian linguistics are presented, and special attention is paid to the way in which lexicography and lexicology have registered the massive changes which have occurred in Russian language since perestrojka. The author describes the development of some important Linguistic schools, like the moskovskaja semantičeskaja škola and the studies about russkaja lingvističeskaja kartina mira. Furthermore there is a description of the National Corpus of Russian Language (available on the internet since 2004) and its possible applications in linguistic research and teaching of the Russian language
- …
