Cognitive applications have become constant companions at our places of work. We expect smart systems to reduce repetitive workloads and support us in uncovering new Knowledge. As a result, data scientists and software engineers are applying various machine learning algorithms to finetune results and increase processing capabilities. At the same time, critics are ever more loudly calling for more transparency about how these cognitive applications actually function. Companies are also advised to not to manage their AI-driven application environment solely on technical grounds.

I present a web service for querying an embedding of entities in the Wikidata knowledge graph. The embedding is trained on the Wikidata dump using Gensim's Word2Vec implementation and a simple graph walk. A REST API is implemented.

Recent research in natural language processing using the program word2vec gives manipulations of word representations that look a lot like semantics produced by vector math. For vector calculations to produce semantics would be remarkable, indeed. The word vectors are drawn from context, big, huge context. And, at least roughly, the meaning of a word is its use (in context). Is it possible some question is begged here?

These days, many organisations have begun to develop their own knowledge graphs. One reason might be to build a solid basis for various machine learning and cognitive computing efforts. For many of those, it remains still unclear where to start. SKOS offers a simple way to start and opens many doors to extend a knowledge graph over time. The usage of open standards for data and knowledge models eliminates proprietary vendor lock-in.

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step approach that utilizes information from knowledge graphs. First, a knowledge-graph representation is learned to embed a large set of entities into a semantic space. Second, an image representation is learned to embed images into the same space. Under this setup, we are able to predict structured properties in the form of relationship triples for any open-world image. This is true even when a set of labels has been omitted from the training protocols of both the knowledge graph and image embeddings. Furthermore, we append this learning framework with appropriate smoothness constraints and show how prior knowledge can be incorporated into the model. Both these improvements combined increase performance for visual recognition by a factor of six compared to our baseline. Finally, we propose a new, extended dataset which we use for experiments.

Embeddings of knowledge graphs have received significant attention due to their excellent performance for tasks like link prediction and entity resolution. In this short paper, we are providing a comparison of two state-of-the-art knowledge graph embeddings for which their equivalence has recently been established, i.e., ComplEx and HolE [Nickel, Rosasco, and Poggio, 2016; Trouillon et al., 2016; Hayashi and Shimbo, 2017]. First, we briefly review both models and discuss how their scoring functions are equivalent. We then analyze the discrepancy of results reported in the original articles, and show experimentally that they are likely due to the use of different loss functions. In further experiments, we evaluate the ability of both models to embed symmetric and antisymmetric patterns. Finally, we discuss advantages and disadvantages of both models and under which conditions one would be preferable to the other.

Knowledge graph embedding aims at offering a numerical knowledge representation paradigm by transforming the entities and relations into continuous vector space. However, existing methods could not characterize the knowledge graph in a fine degree to make a precise link prediction. There are two reasons for this issue: being an ill-posed algebraic system and adopting an overstrict geometric form. As precise link prediction is critical for knowledge graph embedding, we propose a manifold-based embedding principle (ManifoldE) which could be treated as a well-posed algebraic system that expands point-wise modeling in current models to manifold-wise modeling. Extensive experiments show that the proposed models achieve substantial improvements against the state-of-the-art baselines, particularly for the precise prediction task, and yet maintain high efficiency. All of the related poster, slides, datasets and codes have been published in http://www.

In this article, we talk with one of our users: Antonio Messina from the High Performance Computing and Networking Institute of the Italian National Research Council (ICAR-CNR). Antonio (@xMAnton on Twitter) is a Computer Science Engineer who works as an Applied Scientist at the largest public research institution in Italy. His area of expertise includes (No)SQL databases and advanced Unix systems administration, and he likes to get his hands dirty coding mainly in Java and Node.js. He is enthusiastic about technologies such as graph databases and Docker and is constantly looking for innovation in IT. Recently, Antonio successfully submitted a paper that describes a practical use case for GRAKN.AI.

Language in social media is extremely dynamic: new words emerge, trend and disappear, while the meaning of existing words can fluctuate over time. This work addresses several important tasks of visualizing and predicting short term text representation shift, i.e. the change in a word's contextual semantics. We study the relationship between short-term concept drift and representation shift on a large social media corpus — VKontakte collected during the Russia-Ukraine crisis in 2014 — 2015. We visualize short-term representation shift for example keywords and build predictive models to forecast short-term shifts in meaning from previous meaning as well as from concept drift. We show that short-term representation shift can be accurately predicted up to several weeks in advance and that visualization provides insight into meaning change. Our approach can be used to explore and characterize specific aspects of the streaming corpus during crisis events and potentially improve other downstream classification tasks including real-time event forecasting in social media.

Apple fanboys have always had a reputation for undying loyalty to the brand, but Merriam-Webster is taking that characterization to a new level by using them as an example for new dictionary entry "sheeple." According to the newly added word, a "sheeple" is an informal term that is used to describe "people who are docile, compliant, or easily influenced" and can be likened or compared to sheep. To show the word in action, Merriam-Webster included two example sentences, including one that takes a shot at the folks who prefer Apple's computers and mobile devices over the alternatives. "Apple's debuted a battery case for the juice-sucking iPhone--an ungainly lumpy case the sheeple will happily shell out $99 for," the sentence reads. A second, much more innocuous sentence was also included.