Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

Authors: Muhao Chen, Yingtao Tian, Mohan Yang, Carlo Zaniolo

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we evaluate the proposed methods on two cross-lingual tasks: cross-lingual entity matching, and triple-wise alignment verification. We also conduct experiments on two monolingual tasks.
Researcher Affiliation Academia Muhao Chen1, Yingtao Tian2, Mohan Yang1, Carlo Zaniolo1 Department of Computer Science, UCLA1 Department of Computer Science, Stony Brook University2 {muhaochen, yang, zaniolo}@cs.ucla.edu; yittian@cs.stonybrook.edu
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes Experimental results on the trilingual data sets WK3l are reported in this section. WK3l contains English (En), French (Fr), and German (De) knowledge graphs under DBpedia s dbo:Person domain... Meanwhile, we derive another trilingual data set CN3l from Concept Net [Speer and Havasi, 2013].
Dataset Splits No For each language version, 10% triples are selected as the test set, and the remaining becomes the training set. We use 10-fold cross-validation on these cases to train and evaluate the classifier.
Hardware Specification No The paper does not provide any specific details about the hardware used for running experiments, such as GPU or CPU models.
Software Dependencies No The paper does not provide specific software dependencies with version numbers for reproducing the experiments.
Experiment Setup Yes For training, we select the learning rate λ among {0.001, 0.01, 0.1}, α among {1, 2.5, 5, 7.5}, l1 or l2 norm in loss functions, and dimensionality k among {50, 75, 100, 125}. The best configuration on WK3l-15k is λ = 0.01, α = 5, k = 75, l1 norm for Var1, Var2, LM, and CCA, l2 norm for other variants and OT. While the best configuration on WK3l120k is λ = 0.01, α = 5, k = 100, and l2 norm for all models. The training on both data sets takes 400 epochs. We initialize vectors by drawing from a uniform distribution on the unit spherical surface, and initialize matrices using random orthogonal initialization [Saxe et al., 2014].