In this landmark book, Scott Page redefines the way we understand ourselves in relation to one another. The Difference is about how we think in groups--and how our collective wisdom exceeds the sum of its parts. Why can teams of people find better solutions than brilliant individuals working alone? And why are the best group decisions and predictions those that draw upon the very qualities that make each of us unique? The answers lie in diversity--not what we look like outside, but what we look like within, our distinct tools and abilities. The Difference reveals that progress and innovation may depend less on lone thinkers with enormous IQs than on diverse people working together and capitalizing on their individuality. Page shows how groups that display a range of perspectives outperform groups of like-minded experts. Diversity yields superior outcomes, and Page proves it using his own cutting-edge research. Moving beyond the politics that cloud standard debates about diversity, he explains why difference beats out homogeneity, whether you're talking about citizens in a democracy or scientists in the laboratory. He examines practical ways to apply diversity's logic to a host of problems, and along the way offers fascinating and surprising examples, from the redesign of the Chicago "El" to the truth about where we store our ketchup. Page changes the way we understand diversity--how to harness its untapped potential, how to understand and avoid its traps, and how we can leverage our differences for the benefit of all.

Prologue to The Difference: How the Power of Diversity Creates Better Groups, Firms, Schools, and Societies

Pre-trained language representation models, such as BERT, capture a general language representation from large-scale corpora, but lack domain-specific knowledge. When reading a domain text, experts make inferences with relevant knowledge. For machines to achieve this capability, we propose a knowledge-enabled language representation model (K-BERT) with knowledge graphs (KGs), in which triples are injected into the sentences as domain knowledge. However, too much knowledge incorporation may divert the sentence from its correct meaning, which is called knowledge noise (KN) issue. To overcome KN, K-BERT introduces soft-position and visible matrix to limit the impact of knowledge. K-BERT can easily inject domain knowledge into the models by being equipped with a KG without pre-training by itself because it is capable of loading model parameters from the pre-trained BERT. Our investigation reveals promising results in twelve NLP tasks. Especially in domain-specific tasks (including finance, law, and medicine), K-BERT significantly outperforms BERT, which demonstrates that K-BERT is an excellent choice for solving the knowledge-driven problems that require experts.

/pdf/k-bert-enabling-language-representation-with-knowledge-graph-4y3m7ti6a6.pdf

K-BERT: Enabling Language Representation with Knowledge Graph

One of the main challenges that the Semantic Web faces is the integration of a growing number of independently designed ontologies. In this work, we present PARIS, an approach for the automatic alignment of ontologies. PARIS aligns not only instances, but also relations and classes. Alignments at the instance level cross-fertilize with alignments at the schema level. Thereby, our system provides a truly holistic solution to the problem of ontology alignment. The heart of the approach is probabilistic, i.e., we measure degrees of matchings based on probability estimates. This allows PARIS to run without any parameter tuning. We demonstrate the efficiency of the algorithm and its precision through extensive experiments. In particular, we obtain a precision of around 90% in experiments with some of the world's largest ontologies.

PARIS: Probabilistic Alignment of Relations, Instances, and Schema

Recommender system (RS) targets at providing accurate item recommendations to users with respect to their preferences; it has been widely employed in various online applications for addressing the problem of information explosion and improving user experience. In the past decades, while tremendous efforts have been made in enhancing the performance of RSs, some long-standing challenges, such as data sparsity, cold start, and result diversity, are unaddressed. Along this line, an emerging research trend is to exploit the rich semantic information contained in the knowledge graph (KG); it has been proven to be an effective way to enhance the capability of RSs. To this end, we provide a focused survey on KG-based RS via a holistic perspective of both technologies and applications. Specifically, firstly, we briefly review the core concepts and classical algorithms of the RSs and KGs. Secondly, we comprehensively introduce the representative and state-of-the-art works in this field based on different strategies of exploiting KGs for RSs. Meanwhile, we also summarize some typical application scenarios of KG-based RSs, for facilitating the hands-on practices of corresponding algorithms. Finally, we present our opinions on the prospects of KG-based RS and suggest some future research directions in this area.

/pdf/a-survey-on-knowledge-graph-based-recommender-systems-2mm7glxyn0.pdf

A survey on knowledge graph-based recommender systems

Great efforts have been dedicated to harvesting knowledge bases from online encyclopedias These knowledge bases play important roles in enabling machines to understand texts However, most current knowledge bases are in English and non-English knowledge bases, especially Chinese ones, are still very rare Many previous systems that extract knowledge from online encyclopedias, although are applicable for building a Chinese knowledge base, still suffer from two challenges The first is that it requires great human efforts to construct an ontology and build a supervised knowledge extraction model The second is that the update frequency of knowledge bases is very slow To solve these challenges, we propose a never-ending Chinese Knowledge extraction system, CN-DBpedia, which can automatically generate a knowledge base that is of ever-increasing in size and constantly updated Specially, we reduce the human costs by reusing the ontology of existing knowledge bases and building an end-to-end facts extraction model We further propose a smart active update strategy to keep the freshness of our knowledge base with little human costs The 164 million API calls of the published services justify the success of our system

CN-DBpedia: A Never-Ending Chinese Knowledge Extraction System

Entity typing is an essential task for constructing a knowledge base. However, many non-English knowledge bases fail to type their entities due to the absence of a reasonable local hierarchical taxonomy. Since constructing a widely accepted taxonomy is a hard problem, we propose to type these non-English entities with some widely accepted taxonomies in English, such as DBpedia, Yago and Freebase. We define this problem as cross-lingual type inference. In this paper, we present CUTE to type Chinese entities with DBpedia types. First we exploit the cross-lingual entity linking between Chinese and English entities to construct the training data. Then we propose a multi-label hierarchical classification algorithm to type these Chinese entities. Experimental results show the effectiveness and efficiency of our method.

Cross-Lingual Type Inference

This paper addresses the problem ofmulti-instance entity typing from corpus. Current approaches mainly rely on the structured features (\textitattributes, attribute-value pairs andtags ) of the entities. However, their effectiveness is largely dependent on the completeness of structured features, which unfortunately is not guaranteed in KBs. In this paper, we therefore propose to use the text corpus of an entity to infer its types, and propose a multi-instance method to tackle this problem. We take each mention of an entity in KBs as an instance of the entity, and learn the types of these entities from multiple instances. Specifically, we first use an end-to-end neural network model to type each instance of an entity, and then use an integer linear programming (ILP) method to aggregate the predicted type results from multiple instances. Experimental results show the effectiveness of our method.

METIC: Multi-Instance Entity Typing from Corpus

Diversity is one of the important perspectives to characterize behaviors of individuals in social networks. It is intuitively believed that diversity of social ties accounts for competition advantage and idea innovation. However, quantitative evidences in a real large social network can be rarely found in the previous research. Thanks to the availability of scientific publication records on WWW; now we can construct a large scientific collaboration network, which provides us a chance to gain insight into the diversity of relationships in a real social network through statistical analysis. In this article, we dedicate our efforts to perform empirical analysis on a scientific collaboration network extracted from DBLP, an online bibliographic database in computer science, in a systematical way, finding the following: distributions of diversity indices tend to decay in an exponential or Gaussian way; diversity indices are not trivially correlated to existing vertex importance measures; authors of diverse social ties tend to connect to each other and these authors are generally more competitive than others.

Diversity of social ties in scientific collaboration networks

Categories play a fundamental role in human cognition. Defining features (short for DFs) are the key elements to define a category, which enables machines to categorize objects. Categories enriched with their DFs significantly improve the machine's ability of categorization and benefit many applications built upon categorization. However, defining features can rarely be found for categories in current knowledge bases. Traditional efforts such as manual construction by domain experts are not practical to find defining features for millions of categories. In this paper, we make the first attempt to automatically find defining features for millions of categories in the real world. We formalize the defining feature learning problem and propose a bootstrapping solution to learn defining features from the features of entities belonging to a category. Experimental results show the effectiveness and efficiency of our method. Finally, we find defining features for overall 60,247 categories with acceptable accuracy.

Bo Xu

Papers

CN-DBpedia: A Never-Ending Chinese Knowledge Extraction System

Cross-Lingual Type Inference

METIC: Multi-Instance Entity Typing from Corpus

Diversity of social ties in scientific collaboration networks

Learning defining features for categories