Biased graph walks for RDF graph embeddings

Abstract

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.

Global RDF Vector Space Embeddings

“…For all the weighing strategies the processes took between 6 hours for the least demanding strategy, the Predicate Frequency strategy, and up to 48 hours for the most demanding strategy, the Predicate-Object Frequency. The runtime for building the related work approaches, using the publicly available code, 3 was more than a week. …”

“…Following our previous work [3], we apply twelve different strategies for assigning these weights to the edges of the graph. These weights will then in turn bias the random walks on the graph.…”

“…More precisely, we try to identify the most similar pairs of entities in both documents, ignoring the similarity of all the other 1-1 similarities values. The similarity of two documents is then defined as the average maximum similarity for all entities in each document (see [3]). We evaluate performance on document similarity approach using the LP50 dataset [11].…”

Measuring Semantic Coherence of a Conversation

“…For graph embeddings, we use two methods that can be scaled to large graphs, such as DBpedia and Wikidata: biased RDF2Vec [5] (using random walks) and Global RDF Vector Space Embeddings [6]; we refer to the latter ones as KGlove embeddings. RDF2Vec is based on word2vec.…”

“…Knowledge models. We compared the performance on our task across two types of embeddings models trained on two different knowledge source types: GloVe [23] and 10 https://github.com/vendi12/semantic_coherence 11 https://github.com/vendi12/semantic_coherence/tree/master/data 12 https://github.com/rkadlec/ubuntu-ranking-dataset-creator 13 http://model.dbpedia-spotlight.org/en/annotate Word2Vec [20] for the word embeddings, and biased RDF2vec [5] and KGloVe [6] for the knowledge graph entity embeddings.…”