PageRank on Wikipedia: Towards General Importance Scores for Entities

Knowledge Graphs have been recognized as a valuable source for background information in many data mining, information retrieval, natural language processing, and knowledge extraction tasks. However, obtaining a suitable feature vector representation from RDF graphs is a challenging task. In this paper, we extend the RDF2Vec approach, which leverages language modeling techniques for unsupervised feature extraction from sequences of entities. We generate sequences by exploiting local information from graph substructures, harvested by graph walks, and learn latent numerical representations of entities in RDF graphs. We extend the way we compute feature vector representations by comparing twelve di erent edge weighting functions for performing biased walks on the RDF graph, in order to generate higher quality graph embeddings. We evaluate our approach using di erent machine learning, as well as entity and document modeling benchmark data sets, and show that the naive RDF2Vec approach can be improved by exploiting Biased Graph Walks.

show abstract

“…Besides these statistics, we also use PageRank [2] computed for the entities in the knowledge graph [42].…”

Section: Approachmentioning

confidence: 99%

Biased graph walks for RDF graph embeddings

Cochez

Ristoski

Ponzetto

et al. 2017

Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics

View full text Add to dashboard Cite

show abstract

“…Without ranking, the first answer will probably be a small unknown lake in Italy. For this reason we reorder the results using the page rank scores presented in [11] that are available online 12 . Hence, if a user asks for "italian lakes", he will get at a first position in the result list the entity "Lake Como" followed by "Lake Maggiore".…”

Section: Feedback Functionalitymentioning

confidence: 99%

Trill: A Reusable Front-End for QA Systems

Diefenbach

Amjad

Both

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The Semantic Web contains an enormous amount of information in the form of knowledge bases. To make this information available to end-users many question answering (QA) systems over knowledge bases were created in the last years. Their goal is to enable users to access large amounts of structured data in the Semantic Web by bridging the gap between natural language and formal query languages like SPARQL. But automatically generating a SPARQL query from a user's question is not sufficient to bridge the gap between Semantic Web data and the end-users. The result of a SPARQL query consists of a list of URIs and/or literals, which is not a user-friendly presentation of the answer. Such a presentation includes the representation of the URI in the right language and additional information like images, maps, entity summaries and more. We present Trill, the first reusable user-interface (UI) for QA systems over knowledge bases supporting text and audio input, able to present answers from DBpedia and Wikidata in 4 languages (English, French, German, and Italian). It is designed to be used together with Qanary, an infrastructure for composing QA pipelines. This front-end enables the QA community to show their results to end-users and enables the research community to explore new research directions like studying and designing user-interactions with QA systems.

show abstract

“…These approaches use weighting schemes to make certain edges or nodes more likely to be included in the extracted subgraphs than others. Weighting schemes based on metrics such as frequency or PageRank [5,21] tend to favor inclusion of "popular" (or densely connected) nodes in the "representative" subgraphs. This can sometimes lead to inclusion of semantically less relevant nodes and edges in the "representative" subgraphs of target entities [20].…”

Section: Introductionmentioning

confidence: 99%

“…For depth = 1, R2V P R generates the least number of walks. The DBpedia PageRank dataset[21] only provides PageRank values for entities with URIs. Therefore, R2V P R explores the KG only through object properties, excluding datatype properties and literals, resulting in fewer number of walks.…”

mentioning

confidence: 99%

Extracting entity-specific substructures for RDF graph embeddings

Saeed

Chelmis

Prasanna

2019

View full text Add to dashboard Cite

Knowledge Graphs (KGs) are becoming essential to information systems that require access to structured data. Several approaches have been recently proposed, for obtaining vector representations of KGs suitable for Machine Learning tasks, based on identifying and extracting relevant graph substructures using uniform and biased random walks. However, such approaches lead to representations comprising mostly "popular", instead of "relevant", entities in the KG. In KGs, in which different types of entities often exist (such as in Linked Open Data), a given target entity may have its own distinct set of most "relevant" nodes and edges. We propose specificity as an accurate measure of identifying most relevant, entity-specific, nodes and edges. We develop a scalable method based on bidirectional random walks to compute specificity. Our experimental evaluation results show that specificity-based biased random walks extract more "meaningful" (in terms of size and relevance) RDF substructures compared to the state-of-the-art and, the graph embedding learned from the extracted substructures, outperform existing techniques in the task of entity recommendation in DBpedia.

show abstract

PageRank on Wikipedia: Towards General Importance Scores for Entities

Cited by 35 publications

References 11 publications

Biased graph walks for RDF graph embeddings

Biased graph walks for RDF graph embeddings

Trill: A Reusable Front-End for QA Systems

Extracting entity-specific substructures for RDF graph embeddings

Contact Info

Product

Resources

About