Goto

Collaborating Authors

 Semantic Networks


Improved Knowledge Graph Embedding using Background Taxonomic Information

arXiv.org Machine Learning

Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is background taxonomic information (in terms of subclasses and subproperties) that should also be taken into account. We show that existing fully expressive (a.k.a. universal) models cannot provably respect subclass and subproperty information. We show that minimal modifications to an existing knowledge graph completion method enables injection of taxonomic information. Moreover, we prove that our model is fully expressive, assuming a lower-bound on the size of the embeddings. Experimental results on public knowledge graphs show that despite its simplicity our approach is surprisingly effective.


From Word To Sense Embeddings: A Survey on Vector Representations of Meaning

Journal of Artificial Intelligence Research

Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey focuses on the representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their major limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from the word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and applications for this type of representation, and provides an analysis of four of its important aspects: interpretability, sense granularity, adaptability to different domains and compositionality.


Approach for Semi-automatic Construction of Anti-infective Drug Ontology Based on Entity Linking

arXiv.org Artificial Intelligence

The task of entity relation extraction discovers new relation facts and enables broader applications of knowledge graph. Distant supervision is widely adopted for relation extraction, which requires large amounts of texts containing entity pairs as training data. However, in some specific domains such as medicalrelated applications,entity pairs that have certain relations might not appear together, thus it is difficult to meet the requirement for distantly supervised relation extraction. In the light of this challenge, we propose a novel path-based model to discover new entity relation facts. Instead of finding texts for relation extraction, the proposed method extracts path-only information for entity pairs from the current knowledgegraph. For each pair of entities, multiple paths can be extracted, and some of them are more useful for relation extraction than others. In order to capture this observation, we employ attention mechanism to assign different weights for different paths, which highlights the useful paths for entity relation extraction. To demonstrate the effectiveness of the proposed method, we conduct various experiments on a large-scale medical knowledge graph. Compared with the state-of-the-art relation extraction methods using the structure of knowledge graph, the proposed method significantly improves the accuracy of extracted relation factsand achieves the best performance.


Embedding Uncertain Knowledge Graphs

arXiv.org Artificial Intelligence

Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge into machine learning. However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge. The capturing of uncertain knowledge will benefit many knowledge-driven applications such as question answering and semantic search by providing more natural characterization of the knowledge. In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Unlike previous models that characterize relation facts with binary classification techniques, UKGE learns embeddings according to the confidence scores of uncertain relation facts. To further enhance the precision of UKGE, we also introduce probabilistic soft logic to infer confidence scores for unseen relation facts during training. We propose and evaluate two variants of UKGE based on different learning objectives. Experiments are conducted on three real-world uncertain KGs via three tasks, i.e. confidence prediction, relation fact ranking, and relation fact classification. UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results on these tasks, and consistently outperforms baselines on these tasks.


Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors

arXiv.org Artificial Intelligence

Humans convey their intentions through the usage of both verbal and nonverbal behaviors during face-to-face communication. Speaker intentions often vary dynamically depending on different nonverbal contexts, such as vocal patterns and facial expressions. As a result, when modeling human language, it is essential to not only consider the literal meaning of the words but also the nonverbal contexts in which these words appear. To better model human language, we first model expressive nonverbal representations by analyzing the fine-grained visual and acoustic patterns that occur during word segments. In addition, we seek to capture the dynamic nature of nonverbal intents by shifting word representations based on the accompanying nonverbal behaviors. To this end, we propose the Recurrent Attended Variation Embedding Network (RAVEN) that models the fine-grained structure of nonverbal subword sequences and dynamically shifts word representations based on nonverbal cues. Our proposed model achieves competitive performance on two publicly available datasets for multimodal sentiment analysis and emotion recognition. We also visualize the shifted word representations in different nonverbal contexts and summarize common patterns regarding multimodal variations of word representations.


The Enterprise Knowledge Graph

#artificialintelligence

Best conceived of as a "company brain," this knowledge graph focuses on integrating an organization's assortment of people, skills, experiences, materials, essential company databases, and projects, which greatly improves its self-knowledge and thereby yields competitive advantage. Compiled from combing through myriad databases, including those for human resources, emails, and manifold other sources, this knowledge graph provides the foundation for a rapid, detailed assessment of what knowledge and skills a company has at its disposal--and their relation to one another. This graph is designed to create better services and is extremely specific to an organization's industry, line of business, and area of specialization. For example, Google's and Yahoo's search engine endeavors mandate that they collect knowledge about every entity or subject in the world, so they can offer the most relevant, revealing information to their users. LinkedIn's knowledge graph, on the other hand, details people's professions, resumes, and career opportunities.1 Again, the relationships between these nodes are paramount.


Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces

arXiv.org Artificial Intelligence

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the training data. In this paper we put forward a technique that exploits the knowledge encoded in lexical resources, such as Word-Net, to induce embeddings for unseen words. Our approach adapts graph embedding and cross-lingual vector space transformation techniques in order to merge lexical knowledge encoded in ontologies with that derived from corpus statistics. We show that the approach can provide consistent performance improvements across multiple evaluation benchmarks: in-vitro, on multiple rare word similarity datasets, and invivo, in two downstream text classification tasks.


Differentiating Concepts and Instances for Knowledge Graph Embedding

arXiv.org Artificial Intelligence

Concepts, which represent a group of different instances sharing common properties, are essential information in knowledge representation. Most conventional knowledge embedding methods encode both entities (concepts and instances) and relations as vectors in a low dimensional semantic space equally, ignoring the difference between concepts and instances. In this paper, we propose a novel knowledge graph embedding model named TransC by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. We use the relative positions to model the relations between concepts and instances (i.e., instanceOf), and the relations between concepts and sub-concepts (i.e., subClassOf). We evaluate our model on both link prediction and triple classification tasks on the dataset based on YAGO. Experimental results show that TransC outperforms state-of-the-art methods, and captures the semantic transitivity for instanceOf and subClassOf relation. Our codes and datasets can be obtained from https:// github.com/davidlvxin/TransC.


Knowledge Graphs and AI in the Pharma Sector-PoolParty Semantic Suite

#artificialintelligence

With the increasing speed of technological advancements, the pharmaceutical and healthcare industry needs to break up departmental data silos with Knowledge Graphs and AI to understand the value of their data. At PhUSE EU Connect 2018 we will introduce the innovative approach of PoolParty Semantic Suite to make the most out of your data with semantic data integration. Our partner Findwise, global experts in search-driven solutions for the pharmaceutical and healthcare industry, presents a series of four blog posts to help you understand how knowledge graphs and AI can leverage your data-driven innovation and improve healthcare outcome. We face grand societal challenges pinned down in the 17 UN sustainability goals and specifically number 3 Good Health and Well-being. Humans live a longer life, which shifts the population pyramid.


Knowledge Graphs and AI in the Pharma Sector (Part 2)-PoolParty Semantic Suite

#artificialintelligence

In our previous post of this blog post series about knowledge graphs and AI in the pharmaceutical and healthcare industry, you got an overview of the challenges knowledge-intensive organizations face to be able to support data-driven innovation and improve healthcare outcome. In this blog post, you will learn by the hand of a use case about how connecting your siloed departmental data with external authoritative resources will leverage the value of your content assets. Visit us at PhUSE EU Connect 2018, where we will introduce the innovative approach of PoolParty Semantic Suite to make the most out of your data with semantic data integration. Stay tuned for upcoming blog posts that will help you understand how knowledge graphs and AI can leverage your organization. Our partner Findwise, global experts in search-driven solutions for the pharmaceutical and healthcare industry, are bringing all their expertise in information management and knowledge engineering into this blog post series. A smart semantic information engine will connect a variety of information systems relevant within the pharmaceutical and healthcare industry.