In this paper we present Socrates, a deep learning based solutions for Automated Knowledge Base Population. Socrates does not require hand labelled data for domain adaptation. Instead, it exploits a partially populated knowledge base and a large corpus of text documents to train a deep neural network model. As a result of the training process, the system learns how to identify implicit relations between entities across a highly heterogeneous set of documents from various sources, making it suitable for large-scale knowledge extraction from Web documents. We provide an extensive evaluation of the system across three different benchmarks, showing that we consistently improve over state of the art solutions. Remarkably, Socrates ranked first in both the knowledge base population and attribute validation track at the Semantic Web Challenge at ISWC 2017.