Abstract:

Cross-lingual entity alignment algorithms are designed to look for identical real-world objects in multilingual knowledge graphs. This problem occurs, for example, when searching for drugs manufactured in different countries under different names, or when searching for imported equipment. At the moment, there are several open-source libraries that collect implementations of entity alignment algorithms as well as test data sets for various languages. This paper describes experiments with several popular entity alignment algorithms applied to a Russian-English dataset. In addition to translating entity names from Russian to English, experiments on combining the various generators of entity name embeddings with the various generators of relational information embeddings have been conducted. In order to obtain more detailed information about the results of the EA approaches, an assessment by entity types, the number of relationships and attributes have been made. These experiments allowed us to significantly improve the accuracy of several EA algorithms on the English-Russian dataset.

Abstract: It is shown that trust in the content of information resources can be assessed by means of a publishing criterion, with the information recourses being of the trusted and distrusted type. The task of assessment of trust consists of four subtasks: (1) building multisets of physical quantities available in primary data sources, (2) alignment of values of physical quantities, (3) formulation of quantitative restrictions for publishing criterion in different ranges of change of physical quantities, and (4) decomposition of expert data. Spectral data publishing criteria and restrictions required for solving data alignment tasks are outlined. Alignment results have been tabulated. Using vacuum wavenumbers as an example, restrictions inherent in publishing criteria are formulated. The assessment of the content trust obtained from solutions to the tasks of decomposition f expert data are presented as the OWL-ontologies. Building knowledge bases of this kind at virtual data centers intended for data intensive science will provide realization of an automatic selection of spectroscopic information resources exhibiting a high degree of trust.