Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search. Prior conceptual graph construction approaches typically extract high-frequent, coarse-grained, and time-invariant concepts from formal texts. In real applications, however, it is necessary to extract less-frequent, fine-grained, and time-varying conceptual knowledge and build taxonomy in an evolving manner. In this paper, we introduce an approach to implementing and deploying the conceptual graph at Alibaba. Specifically, We propose a framework called AliCG which is capable of a) extracting fine-grained concepts by a novel bootstrapping with alignment consensus approach, b) mining long-tail concepts with a novel low-resource phrase mining approach, c) updating the graph dynamically via a concept distribution estimation method based on implicit and explicit user behaviors. We have deployed the framework at Alibaba UC Browser. Extensive offline evaluation as well as online A/B testing demonstrate the efficacy of our approach.

Ontology is a branch of philosophy dealing with the study of being and existence. However, in a practical business setting, ontology refers to the architecture that binds different sources of information and involves interconnecting data from multiple domains by tagging and categorising. It could be looked at as a means of resolving organisational differences between databases to enhance integration. In AI, ontology refers to a shared vocabulary for researchers. It includes machine-interpretable definitions of basic concepts and the relationships between them.

Metadata vocabularies are used in various domains of study. It provides an in-depth description of the resources. In this work, we develop Algorithm Metadata Vocabulary (AMV), a vocabulary for capturing and storing the metadata about the algorithms (a procedure or a set of rules that is followed step-by-step to solve a problem, especially by a computer). The snag faced by the researchers in the current time is the failure of getting relevant results when searching for algorithms in any search engine. AMV is represented as a semantic model and produced OWL file, which can be directly used by anyone interested to create and publish algorithm metadata as a knowledge graph, or to provide metadata service through SPARQL endpoint. To design the vocabulary, we propose a well-defined methodology, which considers real issues faced by the algorithm users and the practitioners. The evaluation shows a promising result.

Injecting external domain-specific knowledge (e.g., UMLS) into pretrained language models (LMs) advances their capability to handle specialised in-domain tasks such as biomedical entity linking (BEL). However, such abundant expert knowledge is available only for a handful of languages (e.g., English). In this work, by proposing a novel cross-lingual biomedical entity linking task (XL-BEL) and establishing a new XL-BEL benchmark spanning 10 typologically diverse languages, we first investigate the ability of standard knowledge-agnostic as well as knowledge-enhanced monolingual and multilingual LMs beyond the standard monolingual English BEL task. The scores indicate large gaps to English performance. We then address the challenge of transferring domain-specific knowledge in resource-rich languages to resource-poor ones. To this end, we propose and evaluate a series of cross-lingual transfer methods for the XL-BEL task, and demonstrate that general-domain bitext helps propagate the available English knowledge to languages with little to no in-domain data. Remarkably, we show that our proposed domain-specific transfer methods yield consistent gains across all target languages, sometimes up to 20 Precision@1 points, without any in-domain knowledge in the target language, and without any in-domain parallel data.

Medical entity retrieval is an integral component for understanding and communicating information across various health systems. Current approaches tend to work well on specific medical domains but generalize poorly to unseen sub-specialties. This is of increasing concern under a public health crisis as new medical conditions and drug treatments come to light frequently. Zero-shot retrieval is challenging due to the high degree of ambiguity and variability in medical corpora, making it difficult to build an accurate similarity measure between mentions and concepts. Medical knowledge graphs (KG), however, contain rich semantics including large numbers of synonyms as well as its curated graphical structures. To take advantage of this valuable information, we propose a suite of learning tasks designed for training efficient zero-shot entity retrieval models. Without requiring any human annotation, our knowledge graph enriched architecture significantly outperforms common zero-shot benchmarks including BM25 and Clinical BERT with 7% to 30% higher recall across multiple major medical ontologies, such as UMLS, SNOMED, and ICD-10.

Semantic embedding has been widely investigated for aligning knowledge graph (KG) entities. Current methods have explored and utilized the graph structure, the entity names and attributes, but ignore the ontology (or ontological schema) which contains critical meta information such as classes and their membership relationships with entities. In this paper, we propose an ontology-guided entity alignment method named OntoEA, where both KGs and their ontologies are jointly embedded, and the class hierarchy and the class disjointness are utilized to avoid false mappings. Extensive experiments on seven public and industrial benchmarks have demonstrated the state-of-the-art performance of OntoEA and the effectiveness of the ontologies.

It is needless to mention the (already established) overarching importance of knowledge organization and its tried-and-tested high-quality schemes in knowledge-based Artificial Intelligence (AI) systems. But equally, it is also hard to ignore that, increasingly, standalone KOSs are becoming functionally ineffective components for such systems, given their inability to capture the continuous facetization and drift of domains. The paper proposes a radical re-conceptualization of KOSs as a first step to solve such an inability, and, accordingly, contributes in the form of the following dimensions: (i) an explicit characterization of Knowledge Organization Ecosystems (KOEs) (possibly for the first time) and their positioning as pivotal components in realizing sustainable knowledge-based AI solutions, (ii) as a consequence of such a novel characterization, a first examination and characterization of KOEs as Socio-Technical Systems (STSs), thus opening up an entirely new stream of research in knowledge-based AI, and (iii) motivating KOEs not to be mere STSs but STSs which are grounded in Ethics and Responsible Artificial Intelligence cardinals from their very genesis. The paper grounds the above contributions in relevant research literature in a distributed fashion throughout the paper, and finally concludes by outlining the future research possibilities.

Competency Questions (CQs) are used in many ontology engineering methodologies to collect requirements and track the completeness and correctness of an ontology being constructed. Although they are frequently suggested by ontology engineering methodologies, the publicly available datasets of CQs and their formalizations in ontology query languages are very scarce. Since first efforts to automate processes utilizing CQs are being made, it is of high importance to provide large and diverse datasets to fuel these solutions. In this paper, we present BigCQ, the biggest dataset of CQ templates with their formalizations into SPARQL-OWL query templates. BigCQ is created automatically from a dataset of frequently used axiom shapes. These pairs of CQ templates and query templates can be then materialized as actual CQs and SPARQL-OWL queries if filled with resource labels and IRIs from a given ontology. We describe the dataset in detail, provide a description of the process leading to the creation of the dataset and analyze how well the dataset covers real-world examples. We also publish the dataset as well as scripts transforming axiom shapes into pairs of CQ patterns and SPARQL-OWL templates, to make engineers able to adapt the process to their particular needs.

It is a fact that, when developing a new application, it is virtually impossible to reuse, as-is, existing datasets. This difficulty is the cause of additional costs, with the further drawback that the resulting application will again be hardly reusable. It is a negative loop which consistently reinforces itself and for which there seems to be no way out. iTelos is a general purpose methodology designed to break this loop. Its main goal is to generate reusable Knowledge Graphs (KGs), built reusing, as much as possible, already existing data. The key assumption is that the design of a KG should be done middle-out meaning by this that the design should take into consideration, in all phases of the development: (i) the purpose to be served, that we formalize as a set of competency queries, (ii) a set of pre-existing datasets, possibly extracted from existing KGs, and (iii) a set of pre-existing reference schemas, whose goal is to facilitate sharability. We call these reference schemas, teleologies, as distinct from ontologies, meaning by this that, while having a similar purpose, they are designed to be easily adapted, thus becoming a key enabler of itelos.

We assume that substances in the world are represented by two types of concepts, namely substance concepts and classification concepts, the former instrumental to (visual) perception, the latter to (language based) classification. Based on this distinction, we introduce a general methodology for building lexico-semantic hierarchies of substance concepts, where nodes are annotated with the media, e.g., videos or photos, from which substance concepts are extracted, and are associated with the corresponding classification concepts. The methodology is based on Ranganathan's original faceted approach, contextualized to the problem of classifying substance concepts. The key novelty is that the hierarchy is built exploiting the visual properties of substance concepts, while the linguistically defined properties of classification concepts are only used to describe substance concepts. The validity of the approach is exemplified by providing some highlights of an ongoing project whose goal is to build a large scale multimedia multilingual concept hierarchy.