The publisher of Kojien, the most authoritative dictionary in Japan, has been stuck between a rock and a hard place over its definition of Taiwan as a province of China, prompting a request for a correction from the self-ruled island. Since its first publication in 1955, the dictionary has become a household name. The media and other organizations often use it to get the final say on a word's meaning. The seventh edition is slated to be released next month. On Friday, Iwanami Shoten, the publisher, said Kojien's entry on Taiwan is in line with the 1972 Japan-China Joint Communique, in which Japan recognized the People's Republic of China as the sole legal government of China and "fully understands and respects" the PRC's stance that Taiwan is an inalienable part of its territory.

Knowledge representation is a long-history topic in AI, which is very important. A variety of models have been proposed for knowledge graph embedding, which projects symbolic entities and relations into continuous vector space. However, most related methods merely focus on the data-fitting of knowledge graph, and ignore the interpretable semantic expression. Thus, traditional embedding methods are not friendly for applications that require semantic analysis, such as question answering and entity retrieval. To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple. Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple. Extensive experiments show that our model outperforms other state-of-the-art baselines substantially.

The growth of the Web is a success story that has spurred much research in knowledge discovery and data mining. Data mining over Web domains that are unusual is an even harder problem. There are several factors that make a domain unusual. In particular, such domains have significant long tails and exhibit concept drift, and are characterized by high levels of heterogeneity. Notable examples of unusual Web domains include both illicit domains, such as human trafficking advertising, illegal weapons sales, counterfeit goods transactions, patent trolling and cyberattacks, and also non-illicit domains such as humanitarian and disaster relief.

The word2vec method based on skip-gram with negative sampling (Mikolov et al., 2013) [49] was published in 2013 and had a large impact on the field, mainly through its accompanying software package, which enabled efficient training of dense word representations and a straightforward integration into downstream models. In some respects, we have come far since then: Word embeddings have established themselves as an integral part of Natural Language Processing (NLP) models. In other aspects, we might as well be in 2013 as we have not found ways to pre-train word embeddings that have managed to supersede the original word2vec. This post will focus on the deficiencies of word embeddings and how recent approaches have tried to resolve them. If not otherwise stated, this post discusses pre-trained word embeddings, i.e. word representations that have been learned on a large corpus using word2vec and its variants.

Enterprise Knowledge Graph vendors are working hard to find their place in the heart of businesses, helping them do more with and get more out of their mountains of data. Recently, for example, Stardog has adopted its leading Knowledge Graph platform to be "FIBO-aware," mapping to the Financial Industry Business Ontology (FIBO) semantic standards out-of-the-box. GraphPath launched what it says is the first Knowledge-Graph-as-a-Service (KGaaS) platform. And Maana, with its Knowledge Graph-centered Knowledge Platform, has been talking up its partnerships with clients like Shell to drive digital transformation efforts. As part of these efforts, work is underway to make it easier for businesses to adopt these solutions – for experts like data engineers who will manage the graphs, of course, but also for the business users who will consume data from them via different applications that developers create.

This paper shows that a simple baseline based on a Bag-of-Words (BoW) representation learns surprisingly good knowledge graph embeddings. By casting knowledge base completion and question answering as supervised classification problems, we observe that modeling co-occurences of entities and relations leads to state-of-the-art performance with a training time of a few minutes using the open sourced library fastText.

Financial news giant Thomson Reuters has released its Knowledge Graph Feed, a way of instantly visualising the connections between lots of data sources, which it describes as "the first financial social network". The Knowledge Graph system is an open source, standardised data modelling system composed of Permanent Identifiers (PermID) which connect some two billion relationships. Newsweek is hosting an AI and Data Science in Capital Markets conference in NYC, Dec. 6-7. Geoffrey Horrell, director, Product Incubation Financial and Risk, Thomson Reuters, explained: "What we are delivering is like a social network but it's the first financial social network. So you can ask, what are the strategic relationships around the companies and people that you do business with; who are all the officers and directors, who are their suppliers, competitors, associates, affiliates.

Knowledge graphs are a versatile framework to encode richly structured data relationships, but it not always apparent how to combine these with existing entity representations. Methods for retrofitting pre-trained entity representations to the structure of a knowledge graph typically assume that entities are embedded in a connected space and that relations imply similarity. However, useful knowledge graphs often contain diverse entities and relations (with potentially disjoint underlying corpora) which do not accord with these assumptions. To overcome these limitations, we present Functional Retrofitting, a framework that generalizes current retrofitting methods by explicitly modeling pairwise relations. Our framework can directly incorporate a variety of pairwise penalty functions previously developed for knowledge graph completion. We present both linear and neural instantiations of the framework. Functional Retrofitting significantly outperforms existing retrofitting methods on complex knowledge graphs and loses no accuracy on simpler graphs (in which relations do imply similarity). Finally, we demonstrate the utility of the framework by predicting new drug--disease treatment pairs in a large, complex health knowledge graph.

Financial news giant Thomson Reuters has released its Knowledge Graph Feed, a way of instantly visualising the connections between lots of data sources, which it describes as "the first financial social network". The Knowledge Graph system is an open source, standardised data modelling system composed of Permanent Identifiers (PermID) which connect some two billion relationships. Geoffrey Horrell, director, Product Incubation Financial and Risk, Thomson Reuters, explained: "What we are delivering is like a social network but it's the first financial social network. So you can ask, what are the strategic relationships around the companies and people that you do business with; who are all the officers and directors, who are their suppliers, competitors, associates, affiliates. "People have talked about graphs but none of the content providers have really published all their data and all their taxonomies and definitions in this graph format before.

Previous models for learning entity and relationship embeddings of knowledge graphs such as TransE, TransH, and TransR aim to explore new links based on learned representations. However, these models interpret relationships as simple translations on entity embeddings. In this paper, we try to learn more complex connections between entities and relationships. In particular, we use a Convolutional Neural Network (CNN) to learn entity and relationship representations in knowledge graphs. In our model, we treat entities and relationships as one-dimensional numerical sequences with the same length. After that, we combine each triplet of head, relationship, and tail together as a matrix with height 3. CNN is applied to the triplets to get confidence scores. Positive and manually corrupted negative triplets are used to train the embeddings and the CNN model simultaneously. Experimental results on public benchmark datasets show that the proposed model outperforms state-of-the-art models on exploring unseen relationships, which proves that CNN is effective to learn complex interactive patterns between entities and relationships.