Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata

Rudnik, Charlotte; Ehrhart, Thibault; Ferret, Olivier; Teyssou, Denis; Troncy, Raphaël; Tannier, Xavier

doi:10.48550/arxiv.1904.05557

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More and more projects rely on this kind of representation to store their data without compromising the semantics they bear and, as a result, many large-scale Knowledge Graphs, such as Freebase [6], YAGO [30], Wikidata [32], and DBpedia [3] have been published. The success of this graph representation is mainly due to its usefulness in many AIrelated tasks, such as question answering [4,34], recommendation systems [33], and search [29]; as well as in domain-specific applications, for example in the fields of education [12], medicine [28] and finance [22].…”

Section: Introductionmentioning

confidence: 99%

A systematic approach to identify the information captured by Knowledge Graph Embeddings

Ettorre

Bobasheva

Faron-Zucker

et al. 2021

IEEE/WIC/ACM International Conference on Web Intelligence

View full text Add to dashboard Cite

In the last decade Knowledge Graphs have undergone an impressive expansion, mainly due to their extensive use in AI-related applications, such as query answering or recommender systems. This growth has been powered by the expanding landscape of Graph Embedding techniques, which facilitate the manipulation of the vast and sparse information described by Knowledge Graphs. Graph Embedding algorithms create a low-dimensional vector representation of the elements in the graph, i.e. nodes and edges, suitable as input for Machine Learning tasks. Although their effectiveness has been proved on many occasions and for many contexts, the interpretability of such vector representations remains an open issue. In this work, we aim to tackle this issue by providing a systematic approach to decode and make sense of the knowledge captured by Graph Embeddings. We propose a technique for verifying whether Graph Embeddings are able to encode certain properties of the graph elements and we present a categorization for such properties. We test our approach by evaluating the embeddings computed from the same Knowledge Graph through several embedding techniques. We analyze the results on the level of encoding of each property by all the benchmarked algorithms with the final goal of providing insights into the choice of the most suitable technique for each context and encouraging a more conscious use of such approaches.

show abstract