Enterprise and public Knowledge Graphs (KGs) are known to be incomplete. Methods for automatic completion, sometimes by rule learning, scale well. While previous rule-based methods learn closed (non-existential) rules, we introduce Open Path (OP) rules that are constrained existential rules. We present a novel algorithm, OPRL, for learning OP rules. Closed rules complete a KG by answering queries of unclear origin, usually derived from a holdback test set in experimental settings. However, OP rules can generate relevant queries for KG completion. OPRL generates queries even when there is no closed rule to answer the query, or when the correct answer is a missing entity that is not present in the KG. For OPRL to scale well, we propose a novel embedding-based fitness function to efficiently estimate rule quality. Additionally, we introduce a novel, efficient vector computation to formally assess rule quality. We evaluate OPRL using adaptations of Freebase, YAGO2, Wikidata, and a synthetic Poker KG. We find that OPRL mines hundreds of accurate rules from massive KGs with up to 8 M facts. The OP rules generate queries with precision as high as 98% and recall of 62% on a complete KG, demonstrating the first solution for active knowledge graph completion.

Extraction of categorised named entities from text is a complex task given the availability of a variety of Named Entity Recognition (NER) models and the unstructured information encoded in different source document formats. Processing the documents to extract text, identifying suitable NER models for a task, and obtaining statistical information is important in data analysis to make informed decisions. This paper presents\footnoteThe manuscript follows guidelines to showcase a demonstration that introduces an overview of how the toolkit works: input document set, initial settings, processing, and output set. The input document set is artificial in order to show various toolkit capabilities. TNNT, a toolkit that automates the extraction of categorised named entities from unstructured information encoded in source documents, using diverse state-of-the-art (SOTA) Natural Language Processing (NLP) tools and NER models.TNNT integrates 21 different NER models as part of a Knowledge Graph Construction Pipeline (KGCP) that takes a document set as input and processes it based on the defined settings, applying the selected blocks of NER models to output the results. The toolkit generates all results with an integrated summary of the extracted entities, enabling enhanced data analysis to support the KGCP, and also, to aid further NLP tasks.

It is natural and effective to use rules for representing explicit knowledge in knowledge graphs. However, it is challenging to learn rules automatically from very large knowledge graphs such as Freebase and YAGO. This paper presents a new approach, RLvLR (Rule Learning via Learning Representations), to learning rules from large knowledge graphs by using the technique of embedding in representation learning together with a new sampling method. Based on RLvLR, a new method RLvLR-Stream is developed for learning rules from streams of knowledge graphs. Both RLvLR and RLvLR-Stream have been implemented and experiments conducted to validate the proposed methods regarding the tasks of rule learning and link prediction. Experimental results show that our systems are able to handle the task of rule learning from large knowledge graphs with high accuracy and outperform some state-of-the-art systems. Specifically, for massive knowledge graphs with hundreds of predicates and over 10M facts, RLvLR is much faster and can learn much more quality rules than major systems for rule learning in knowledge graphs such as AMIE+. In the setting of knowledge graph streams, RLvLR-Stream significantly improved RLvLR for both rule learning and link prediction.

We study the problem of learning first-order rules from large Knowledge Graphs (KGs). With recent advancement in information extraction, vast data repositories in the KG format have been obtained such as Freebase and YAGO. However, traditional techniques for rule learning are not scalable for KGs. This paper presents a new approach RLvLR to learning rules from KGs by using the technique of embedding in representation learning together with a new sampling method. Experimental results show that our system outperforms some state-of-the-art systems. Specifically, for massive KGs with hundreds of predicates and over 10M facts, RLvLR is much faster and can learn much more quality rules than major systems for rule learning in KGs such as AMIE+. We also used the RLvLR-mined rules in an inference module to carry out the link prediction task. In this task, RLvLR outperformed Neural LP, a state-of-the-art link prediction system, in both runtime and accuracy.