Baichuan Zhang

TL;DR: Zhang et al. as mentioned in this paper proposed a novel name disambiguation method which leverages only relational data in the form of anonymized graphs and used a novel representation learning model to embed each document in a low dimensional vector space.

TL;DR: This work created three types of information net- works from the historical job data: (i) job transition network, (ii) job-skill network, and (iii) skill co-occurrence network which can utilize the information from all three networks to jointly learn the representation of the jobs and skills in the shared k-dimensional latent space.

TL;DR: In this paper, the authors propose an end-to-end framework for developing custom knowledge graph driven analytics for arbitrary application domains, which combines curated knowledge graphs along with knowledge extracted from unstructured text, support for advanced trending and explanatory questions on a dynamic KG, and ability to answer queries where the answer is embedded across multiple data sources.

TL;DR: This work proposes an end-toend framework for developing custom knowledge graph driven analytics for arbitrary application domains and highlights the uniqueness of this system in its combination of curated KGs along with knowledge extracted from unstructured text.

TL;DR: This work proposes a Latent Feature Embedding based link recommendation model for prediction task and utilizes Bayesian Personalized Ranking based optimization technique for learning models for each predicate.