Save the date for this informative day of online presentations on how the Neo4j graph database and Neo4j Bloom are powering mission-critical applications in the Telecommunications industry. Sign up to get more info on Neo4j presentation topics and speakers as it becomes available. If you're unable to make the full day of talks, that's okay! All talks will be sent out to registered attendees after the event.

We argue that the next frontier in natural language understanding (NLU) and generation (NLG) will include models that can efficiently access external structured knowledge repositories. In order to support the development of such models, we release the VisualSem knowledge graph (KG) which includes nodes with multilingual glosses and multiple illustrative images and visually relevant relations. We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG. This multi-modal retrieval model can be integrated into any (neural network) model pipeline and we encourage the research community to use VisualSem for data augmentation and/or as a source of grounding, among other possible uses. VisualSem as well as the multi-modal retrieval model are publicly available and can be downloaded in: https://github.com/iacercalixto/visualsem.

In this work, we present a new dataset for conversational recommendation over knowledge graphs in e-commerce platforms called COOKIE. The dataset is constructed from an Amazon review corpus by integrating both user-agent dialogue and custom knowledge graphs for recommendation. Specifically, we first construct a unified knowledge graph and extract key entities between user--product pairs, which serve as the skeleton of a conversation. Then we simulate conversations mirroring the human coarse-to-fine process of choosing preferred items. The proposed baselines and experiments demonstrate that our dataset is able to provide innovative opportunities for conversational recommendation.

The taxation of multi-national companies is a complex field, since it is influenced by the legislation of several states. Laws in different states may have unforeseen interaction effects, which can be exploited by allowing multinational companies to minimize taxes, a concept known as tax planning. In this paper, we present a knowledge graph of multinational companies and their relationships, comprising almost 1.5M business entities. We show that commonly known tax planning strategies can be formulated as subgraph queries to that graph, which allows for identifying companies using certain strategies. Moreover, we demonstrate that we can identify anomalies in the graph which hint at potential tax planning strategies, and we show how to enhance those analyses by incorporating information from Wikidata using federated queries.

Recent advances in information extraction have motivated the automatic construction of huge Knowledge Graphs (KGs) by mining from large-scale text corpus. However, noisy facts are unavoidably introduced into KGs that could be caused by automatic extraction. To validate the correctness of facts (i.e., triplets) inside a KG, one possible approach is to map the triplets into vector representations by capturing the semantic meanings of facts. Although many representation learning approaches have been developed for knowledge graphs, these methods are not effective for validation. They usually assume that facts are correct, and thus may overfit noisy facts and fail to detect such facts. Towards effective KG validation, we propose to leverage an external human-curated KG as auxiliary information source to help detect the errors in a target KG. The external KG is built upon human-curated knowledge repositories and tends to have high precision. On the other hand, although the target KG built by information extraction from texts has low precision, it can cover new or domain-specific facts that are not in any human-curated repositories. To tackle this challenging task, we propose a cross-graph representation learning framework, i.e., CrossVal, which can leverage an external KG to validate the facts in the target KG efficiently. This is achieved by embedding triplets based on their semantic meanings, drawing cross-KG negative samples and estimating a confidence score for each triplet based on its degree of correctness. We evaluate the proposed framework on datasets across different domains. Experimental results show that the proposed framework achieves the best performance compared with the state-of-the-art methods on large-scale KGs.

Open Government Data (OGD) is being published by various public administration organizations around the globe. Within the metadata of OGD data catalogs, the publishing organizations (1) are not uniquely and unambiguously identifiable and, even worse, (2) change over time, by public administration units being merged or restructured. In order to enable fine-grained analyses or searches on Open Government Data on the level of publishing organizations, linking those from OGD portals to publicly available knowledge graphs (KGs) such as Wikidata and DBpedia seems like an obvious solution. Still, as we show in this position paper, organization linking faces significant challenges, both in terms of available (portal) metadata and KGs in terms of data quality and completeness. We herein specifically highlight five main challenges, namely regarding (1) temporal changes in organizations and in the portal metadata, (2) lack of a base ontology for describing organizational structures and changes in public knowledge graphs, (3) metadata and KG data quality, (4) multilinguality, and (5) disambiguating public sector organizations. Based on available OGD portal metadata from the Open Data Portal Watch, we provide an in-depth analysis of these issues, make suggestions for concrete starting points on how to tackle them along with a call to the community to jointly work on these open challenges.

Commonsense knowledge graph reasoning(CKGR) is the task of predicting a missing entity given one existing and the relation in a commonsense knowledge graph (CKG). Existing methods can be classified into two categories generation method and selection method. Each method has its own advantage. We theoretically and empirically compare the two methods, finding the selection method is more suitable than the generation method in CKGR. Given the observation, we further combine the structure of neural Text Encoder and Knowledge Graph Embedding models to solve the selection method's two problems, achieving competitive results. We provide a basic framework and baseline model for subsequent CKGR tasks by selection methods.

Capturing the composition patterns of relations is a vital task in knowledge graph completion. It also serves as a fundamental step towards multi-hop reasoning over learned knowledge. Previously, rotation-based translational methods, e.g., RotatE, have been developed to model composite relations using the product of a series of complex-valued diagonal matrices. However, RotatE makes several oversimplified assumptions on the composition patterns, forcing the relations to be commutative, independent from entities and fixed in scale. To tackle this problem, we have developed a novel knowledge graph embedding method, named DensE, to provide sufficient modeling capacity for complex composition patterns. In particular, our method decomposes each relation into an SO(3) group-based rotation operator and a scaling operator in the three dimensional (3-D) Euclidean space. The advantages of our method are twofold: (1) For composite relations, the corresponding diagonal relation matrices can be non-commutative and related with entity embeddings; (2) It extends the concept of RotatE to a more expressive setting with lower model complexity and preserves the direct geometrical interpretations, which reveals how relations with distinct patterns (i.e., symmetry/anti-symmetry, inversion and composition) are modeled. Experimental results on multiple benchmark knowledge graphs show that DensE outperforms the current state-of-the-art models for missing link prediction, especially on composite relations.

In this paper, we study the problem of learning continuous vector representations of knowledge graphs for predicting missing links. We present a new approach called ConEx, which infers missing links by leveraging the composition of a 2D convolution with a Hermitian inner product of complex-valued embedding vectors. We evaluate ConEx against state-of-the-art approaches on the WN18RR, FB15K-237, KINSHIP and UMLS benchmark datasets. Our experimental results show that ConEx achieves a performance superior to that of state-of-the-art approaches such as RotatE, QuatE and TuckER on the link prediction task on all datasets while requiring at least 8 times fewer parameters. We ensure the reproducibility of our results by providing an open-source implementation which includes the training, evaluation scripts along with pre-trained models at https://github.com/conex-kge/ConEx.

Don't try to put the cart before the horse: realize that efficient data preparation (and thus interoperable standards) and data quality, especially in the enterprise environment, are a basic requirement for all applications of artificial intelligence. The development of competences and experts in the field of artificial intelligence must take place at least parallel to the process of every technological decision, but not at the end of the implementation of an AI strategy. Outsourcing must not be part of this strategy. 'Not to boil the ocean', in other words: small, agile, consecutive pilot projects alone are not enough to develop an AI strategy. Parallel to the pilot phase, a more far-reaching strategy should be developed together with the management to promote cross-departmental, process-independent and data-driven decision-making and activities.