Multi-interest recommendation is essential for the matching stage. By generating multiple user representations, it can better cover the diverse interests derived from user interaction history. Ideally, multi-interest models should effectively identify the underlying latent factors — the specific themes, intents, or preferences — within historical behaviors. However, conventional methods typically rely on weighted aggregation (e.g., Attention), which we argue leads to over-smoothed representations. This aggregation dilutes the intensity of significant patterns that appear only locally, blending them into a blurry average. To address this, we propose DMI, a model-agnostic diffusion framework that distills precise interests by amplifying co-occurring latent factors across behaviors. Distinct from prior diffusion works that reconstruct the single next item—which risks collapsing diverse interests—DMI reconstructs the interest vectors themselves to preserve their distributional independence. To support this, we introduce a cross-transformer module that adaptively extracts interest-specific information from designated historical interactions, transforming the diffusion process from an unconditional one into a guided, interest-disentangled pathway. In addition, we design a gradient back-propagation strategy to decouple the joint optimization of the reconstruction and recommendation losses, thereby improving training stability. Extensive offline experiments demonstrate DMI's superiority over existing methods, achieving an average relative improvement of 11.2% across all metrics on Amazon Books datasets while increasing recommendation diversity by 11.8%. Successfully deployed in a real-world recommender system, DMI effectively enhances user satisfaction and system performance at scale, serving the major traffic of hundreds of millions of daily active users.

With the development of the Semantic Web and Artificial Intelligence techniques, ontology has become a very powerful way of representing not only knowledge but also their semantics. Therefore, how to construct ontologies from existing data sources has become an important research topic. In this paper, an approach for constructing ontologies by mining deep semantics from eXtensible Markup Language (XML) Schemas (including XML Schema 1.0 and XML Schema 1.1) and XML instance documents is proposed. Given an XML Schema and its corresponding XML instance document, 34 rules are first defined to mine deep semantics from the XML Schema. The mined semantics is formally stored in an intermediate conceptual model and then is used to generate an ontology at the conceptual level. Further, an ontology population approach at the instance level based on the XML instance document is proposed. Now, a complete ontology is formed. Also, some corresponding core algorithms are provided. Finally, a prototype system is implemented, which can automatically generate ontologies from XML Schemas and populate ontologies from XML instance documents. The paper also classifies and summarizes the existing work and makes a detailed comparison. Case studies on real XML data sets verify the effectiveness of the approach.

Currently, named entity recognition (NER) is mainly evaluated on standard and well-annotated data sets. However, the construction of a well-annotated data set will consume a lot of manpower and time. In lots of applications of NER, data sets may contain a lot of noise, and a large part of noise comes from unlabeled entities. At present, the training process of most models treat unlabeled entities as nonentities, which causes these models to lean toward predicting most words of an input context as nonentities and greatly affects their performances. In this paper, as the first attempt, we innovatively propose an adaptive positive-unlabeled (adaPU) learning technology, and integrate the adaPU into a machine reading comprehension (MRC) framework for NER, which can still perform well on data sets with a large proportion of unlabeled entities. In our framework, to leverage the above problem that a model may predict most words of an input context as nonentities, we propose an adaPU learning technology by adjusting a loss coefficient of positive and negative samples. Moreover, instead of just constructing a fixed query for each entity type as input to MRC, we propose a new method of dynamically constructing multiple queries for each entity type, which also brings slight performance improvement for NER. Accordingly, we explore new training and entity inference strategies for our learning framework. The experimental results show that our framework is effective on data sets that contain a large number of unlabeled entities. When the proportion of unlabeled entities reaches 50%, our framework still can keep from losing effectiveness and maintain more than 80 F1-scores on several data sets. Also, the experiments show that our framework can achieve better or competitive performance on standard data sets. The ablation experiments further fully demonstrate our MRC framework with adaPU learning and dynamic query construction method can improve the performance of NER.

A significant interest developed regarding the problem of describing databases with expressive knowledge representation techniques in recent years, so that database reasoning may be handled intelligently. Therefore, it is possible and meaningful to investigate how to reason on fuzzy relational databases (FRDBs) with fuzzy ontologies. In this paper, we first propose a formal approach and an automated tool for constructing fuzzy ontologies from FRDBs, and then we study how to reason on FRDBs with constructed fuzzy ontologies. First, we give their respective formal definitions of FRDBs and fuzzy Web Ontology Language (OWL) ontologies. On the basis of this, we propose a formal approach that can directly transform an FRDB (including its schema and data information) into a fuzzy OWL ontology (consisting of the fuzzy ontology structure and instance). Furthermore, following the proposed approach, we implement a prototype construction tool called FRDB2FOnto. Finally, based on the constructed fuzzy OWL ontologies, we investigate how to reason on FRDBs (e.g., consistency, satisfiability, subsumption, and redundancy) through the reasoning mechanism of fuzzy OWL ontologies, so that the reasoning of FRDBs may be done automatically by means of the existing fuzzy ontology reasoner.© 2012 Wiley Periodicals, Inc.

Extracting domain knowledge from databases can facilitate the development of Web ontologies. In this paper, a formal approach and an automated tool for constructing ontologies from Object-oriented database models (OODMs) are developed. The approach and tool can automatically translate an OODM and its corresponding database instances into the ontology structure and ontology instances, respectively. Case studies show that the approach is feasible and the automated construction tool is efficient.

How to quickly and cheaply construct Web ontologies has become a key technology to enable the Semantic Web. Classical ontologies are not sufficient for handling imprecise and uncertain information that is commonly found in many application domains. In this paper, we propose an approach for constructing fuzzy ontologies from fuzzy UML models, in which the fuzzy ontology consists of fuzzy ontology structure and instances. Firstly, the fuzzy UML model is investigated in detail, and a kind of formal definition of fuzzy UML models is proposed. Then, a kind of fuzzy ontology called fuzzy OWL DL ontology is introduced. Furthermore, we consider the fuzzy UML model and the corresponding fuzzy UML instantiations (i.e., object diagrams) simultaneously, and translate them into the fuzzy ontology structure and the fuzzy ontology instances, respectively. In addition, since a fuzzy OWL DL ontology is equivalent to a fuzzy Description Logic f-SHOIN(D) knowledge base, how the reasoning problems of fuzzy UML models (e.g., consistency, subsumption, equivalence, and redundancy) may be reasoned through reasoning mechanism of f-SHOIN(D) is investigated, which can help to construct fuzzy ontologies more exactly.

How to quickly and cheaply construct Web ontologies has become a key technology to enable the Semantic Web. However, information imprecision and uncertainty exist in many real-world applications. Thus constructing fuzzy ontology by extracting domain knowledge from fuzzy database model such as fuzzy ER model can profitably support fuzzy ontology development. In this paper, firstly, we give the formal definition and semantics of fuzzy ER model. Then, we introduce a kind of fuzzy extension of OWL DL, named fuzzy OWL DL. Furthermore, based on the fuzzy OWL DL, the formal definition and Model-Theoretic semantics of fuzzy OWL DL ontology are given. Whatpsilas more, we realize the formal translation from fuzzy ER model to fuzzy OWL DL ontology by a semantics-preserving translation algorithm. Finally, since a fuzzy OWL DL ontology is being equivalent to a description logic f-SHOIN(D) knowledge base, the reasoning problem of satisfiability, subsumption, and redundancy of fuzzy ER model may reason automatically through reasoning mechanism of f-SHOIN(D) is also investigated, which can contribute to constructing fuzzy OWL DL ontologys exactly that meet applicationpsilas needs.