Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach

Gusmão, Arthur Colombini; Correia, Alvaro H. C.; Bona, Glauber De; Cozman, Fábio Gagliardi

doi:10.48550/arxiv.1806.09504

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The coherence measure allows automated evaluation of the quality of topics learned by topic modelling methods by using additional Point-wise Mutual Information (PMI) for word pairs. In [12], authors adopt ''pedagogical approaches'' to interpret KGEs and extract weighted Horn rules to increase their interpretability. In the work [3], authors present a model that does predict links and decides whether it is a ''topical'' or a ''social'' link.…”

Section: Interpreting Knowledge Graph Embeddingsmentioning

confidence: 99%

“…Authors from [5] regularize embeddings incorporating additional entity co-occurrence statistics from text data, thus inducing interpretability in the embeddings. [12] extract weighted Horn rules from embeddings to interpret them. In the area of word embeddings, different authors proposed various models for modelling sparse word-embeddings [23,34].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Regularized online tensor factorization for sparse knowledge graph embeddings

Zulaika

Almeida

López‐de‐Ipiña

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Knowledge Graphs represent real-world facts and are used in several applications; however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. Embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable Knowledge Graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add $$l_1$$ l 1 regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics.

show abstract

Section: Interpreting Knowledge Graph Embeddingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%