In this paper, we introduce the problem of knowledge graph contextualization - that is, given a specific context, the problem of extracting the most relevant sub-graph of a given knowledge graph. The context in the case of this paper is defined to be the textual entailment problem, and more specifically an instance of that problem where the entailment relationship between two sentences P and H has to be predicted automatically. This prediction takes the form of a classification task, and we seek to provide that task with the most relevant external knowledge while eliminating as much noise as possible. We base our methodology on finding the shortest paths in the cost-customized external knowledge graph that connect P and H, and build a series of methods - starting with manually curated search heuristics and culminating in automatically extracted heuristics - to find such paths and build the most relevant sub-graph. We evaluate our approaches by measuring the accuracy of the classification on the textual entailment problem, and show that modulating the external knowledge that is used has an impact on performance. 1 Introduction Knowledge Graphs (KGs) contain a very large amount of knowledge about the world and phenomena within it. Such knowledge can be very useful in natural language processing (NLP) tasks such as question answering, textual entailment etc. - tasks that can benefit from a large amount of specialized, domain-specific knowledge. However, recent approaches that have tried to use KGs as sources of external knowledge for the textual entailment problem (Wang et al. 2019) have found that bringing in external knowledge from KGs comes with a significant downside - namely noise that is brought in from the external knowledge. This noise mainly occurs due to the fact that KGs are very large graphs that often contain wrong, repeated, and incomplete information. Retrieving a sub-graph of a given KG that is relevant to a given problem instance is a nontrivial task, and continues to be a topic of much research study.

Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic contextual nature, i.e., entities and relations may appear in different graph contexts, and accordingly, exhibit different properties. This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings. Two types of graph contexts are studied: edges and paths, both formulated as sequences of entities and relations. CoKE takes a sequence as input and uses a Transformer encoder to obtain contextualized representations. These representations are hence naturally adaptive to the input, capturing contextual meanings of entities and relations therein. Evaluation on a wide variety of public benchmarks verifies the superiority of CoKE in link prediction and path query answering. It performs consistently better than, or at least equally well as current state-of-the-art in almost every case, in particular offering an absolute improvement of 19.7% in H@10 on path query answering. Our code is available at \url{https://github.com/paddlepaddle/models/tree/develop/PaddleKG/CoKE}.

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate bias. In natural language processing, gender bias has been shown to exist in context-free word embeddings. Recently, contextual word representations have outperformed word embeddings in several downstream NLP tasks. These word representations are conditioned on their context within a sentence, and can also be used to encode the entire sentence. In this paper, we analyze the extent to which state-of-the-art models for contextual word representations, such as BERT and GPT-2, encode biases with respect to gender, race, and intersectional identities. Towards this, we propose assessing bias at the contextual word level. This novel approach captures the contextual effects of bias missing in context-free word embeddings, yet avoids confounding effects that underestimate bias at the sentence encoding level. We demonstrate evidence of bias at the corpus level, find varying evidence of bias in embedding association tests, show in particular that racial bias is strongly encoded in contextual word models, and observe that bias effects for intersectional minorities are exacerbated beyond their constituent minority identities. Further, evaluating bias effects at the contextual word level captures biases that are not captured at the sentence level, confirming the need for our novel approach.

In this paper, we study the problem of learning probabilistic logical rules for inductive and interpretable link prediction. Despite the importance of inductive link prediction, most previous works focused on transductive link prediction and cannot manage previously unseen entities. Moreover, they are black-box models that are not easily explainable for humans. We propose DRUM, a scalable and differentiable approach for mining first-order logical rules from knowledge graphs which resolves these problems. We motivate our method by making a connection between learning confidence scores for each rule and low-rank tensor approximation. DRUM uses bidirectional RNNs to share useful information across the tasks of learning rules for different relations. We also empirically demonstrate the efficiency of DRUM over existing rule mining methods for inductive link prediction on a variety of benchmark datasets.

Knowledge Graphs (KGs) are composed of structured information about a particular domain in the form of entities and relations. In addition to the structured information KGs help in facilitating interconnectivity and interoperability between different resources represented in the Linked Data Cloud. KGs have been used in a variety of applications such as entity linking, question answering, recommender systems, etc. However, KG applications suffer from high computational and storage costs. Hence, there arises the necessity for a representation able to map the high dimensional KGs into low dimensional spaces, i.e., embedding space, preserving structural as well as relational information. This paper conducts a survey of KG embedding models which not only consider the structured information contained in the form of entities and relations in a KG but also the unstructured information represented as literals such as text, numerical values, images, etc. Along with a theoretical analysis and comparison of the methods proposed so far for generating KG embeddings with literals, an empirical evaluation of the different methods under identical settings has been performed for the general task of link prediction.

Companies that develop and build Knowledge Graphs are taking large amounts of data from various data silos and adding value to it so it can be used in a meaningful and more intelligent way. Download this presentation to learn how our customers are using Knowledge Graphs to drive the business value of their data and strengthen their AI strategy.

Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets Esma Balkır 1,2*, Masha Naslidnyk 2, Dave Palfrey 2 and Arpit Mittal 2 1 University of Edinburgh, Scotland, UK 2 Amazon Research, Cambridge, UK 1 esma.balkir@ed.ac.uk 2 { naslidny, dpalfrey, mitarpit }@amazon.co.uk Abstract Bilinear models such as DistMult and ComplEx are effective methods for knowledge graph (KG) completion. However, they require large batch sizes, which becomes a performance bottleneck when training on large scale datasets due to memory constraints. In this paper we use occurrences of entity-relation pairs in the dataset to construct a joint learning model and to increase the quality of sampled negatives during training. We show on three standard datasets that when these two techniques are combined, they give a significant improvement in performance, especially when the batch size and the number of generated negative examples are low relative to the size of the dataset. We then apply our techniques to a dataset containing 2 million entities and demonstrate that our model outperforms the baseline by 2.8% absolute on hits@1. 1 Introduction A Knowledge Graph (KG) is a collection of facts which are stored as triples, e.g. Even though knowledge graphs are essential for various NLP tasks, open domain knowledge graphs have missing facts.

Given a natural language phrase, relation linking aims to find a relation (predicate or property) from the underlying knowledge graph to match the phrase. It is very useful in many applications, such as natural language question answering, personalized recommendation and text summarization. However, the previous relation linking algorithms usually produce a single relation for the input phrase and pay little attention to a more general and challenging problem, i.e., combinational relation linking that extracts a subgraph pattern to match the compound phrase (e.g. In this paper, we focus on the task of combinational relation linking over knowledge graphs. To resolve the problem, we design a systematic method based on the data-driven relation assembly technique, which is performed under the guidance of meta patterns. We also introduce external knowledge to enhance the system understanding ability. Finally, we conduct extensive experiments over the real knowledge graph to study the performance of the proposed method. 1 Introduction Knowledge graphs have been important repositories to materialize a huge amount of structured information in the form of triples, where a triple consists of nullsubject, predicate, objectnull or null subject, property, value null. There have been many such knowledge graphs, e.g., DBpedia (Auer et al. 2007), Y ago (Suchanek, Kasneci, and Weikum 2007), and Freebase (Bollacker et al. 2008). In order to bridge the gap between unstructured text (including text documents and natural language questions) and structured knowledge, an important and interesting task is conducting relation linking over the knowledge graph, i.e., finding the specific predicates/properties from the knowledge graph that match the phrases detected in the sentence (also may be a question). Relation linking can power many downstream applications. As a friendly and intuitive approach to exploring knowledge graphs, using natural language questions to query the knowledge graph has attracted a lot of attentions in both academia and industrial communities (Berant et al. 2013; Bao et al. 2016; Das et al. 2017; Hu et al. 2018; Huang et al. 2019). Generally, the simple questions, e.g., who is the founder of Microsoft, are easy to answer since Figure 1: Example of combinational relations matching the compound phrase mother-in-law. it is straightforward to choose the predicate "founder" from the knowledge graph that matches the phrase "founder" in the input question.

Natural language question answering over knowledge graphs is an important and interesting task as it enables common users to gain accurate answers in an easy and intuitive manner. However, it remains a challenge to bridge the gap between unstructured questions and structured knowledge graphs. To address the problem, a natural discipline is building a structured query to represent the input question. Searching the structured query over the knowledge graph can produce answers to the question. Distinct from the existing methods that are based on semantic parsing or templates, we propose an effective approach powered by a novel notion, structural query pattern, in this paper. Given an input question, we first generate its query sketch that is compatible with the underlying structure of the knowledge graph. Then, we complete the query graph by labeling the nodes and edges under the guidance of the structural query pattern. Finally, answers can be retrieved by executing the constructed query graph over the knowledge graph. Evaluations on three question answering benchmarks show that our proposed approach outperforms state-of-the-art methods significantly.