Deep learning models achieve state-of-the-art per-formance in solving the task of Entity Matching, which aims to identify records that refer to the same real-world entity. However, they act as black-box models for the user, who has limited insights into the rationales behind their decisions. Several explainers (e.g., LIME, Mojito, Landmark, LEMON, and CERTA) have been proposed in the literature to address this issue. Their main focus is to generate explanations that are faithful to the model without considering their comprehensibility to the user. For example, verbose explanations could be very complex to analyze, hindering the model's understanding. In this paper, we propose CREW, an explanation system for Entity Matching models that combines the comprehensibility of the explanations and fidelity to the model. To achieve this, CREW creates explanations as clusters of words. The clusters are created by exploiting three different forms of knowledge: the semantic similarity of the words, their arrangement into the dataset attributes, and their importance in explaining the model. Experiments show that CREW generates explanations that are more interpretable for the user and more faithful to the model than those generated by competing explanation techniques.

We explore the use of Relational Database Manage-ment Systems to reduce technical debt in Machine Learning de-ployments, specifically focusing on in-DBMS prediction serving. We evaluate the performance of ML pipelines in Sklearn and ML.NET against their SQL counterparts executed on MySQL and SQL Server. Results suggest comparable performance when data resides in the database, indicating the potential feasibility of executing prediction processes directly in SQL on DBMSs.

This paper showcases Time2Feat, an end-to-end machine learning system for Multivariate Time Series (MTS) clustering. The system relies on interpretable inter-signal and intra-signal features extracted from the time series. Then, a dimensionality reduction technique is applied to select a subset of features that retain most of the information, thus enhancing the interpretability of the results. In addition, the system enables domain specialists to semi-supervise the process by submitting a small collection of MTS with a target cluster. This process further improves both accuracy and interpretability, by reducing the number of features used by the clustering process. The demonstration shows the application of Time2Feat to various MTS datasets, by creating clusters from MTS datasets of interest, experimenting with different settings and using the approach capabilities to interpret the clusters generated.

In the past decade, many approaches have been suggested to execute ML workloads on a DBMS. However, most of them have looked at in-DBMS ML from a training perspective, whereas ML inference has been largely overlooked. We think that this is an important gap to fill for two main reasons: (1) in the near future, every application will be infused with some sort of ML capability; (2) behind every web page, application, and enterprise there is a DBMS, whereby in-DBMS inference is an appealing solution both for efficiency (e.g., less data movement), performance (e.g., cross-optimizations between relational operators and ML) and governance. In this article, we study whether DBMSs are a good fit for prediction serving. We introduce a technique for translating trained ML pipelines containing both featurizers (e.g., one-hot encoding) and models (e.g., linear and tree-based models) into SQL queries, and we compare in-DBMS performance against popular ML frameworks such as Sklearn and ml.net. Our experiments show that, when pushed inside a DBMS, trained ML pipelines can have performance comparable to ML frameworks in several scenarios, while they perform quite poorly on text featurization and over (even simple) neural networks.

Clustering multivariate time series is a critical task in many real-world applications involving multiple signals and sensors. Existing systems aim to maximize effectiveness, efficiency and scalability, but fail to guarantee the interpretability of the results. This hinders their application in critical real scenarios where human comprehension of algorithmic behavior is required. This paper introduces Time2Feat, an end-to-end machine learning system for multivariate time series (MTS) clustering. The system relies on inter-signal and intra-signal interpretable features extracted from the time series. Then, a dimensionality reduction technique is applied to select a subset of features that retain most of the information, thus enhancing the interpretability of the results. In addition, domain experts can semi-supervise the process, by providing a small amount of MTS with a target cluster. This process further improves both accuracy and interpretability, narrowing down the number of features used by the clustering process. We demonstrate the effectiveness, interpretability, efficiency, and robustness of Time2Feat through experiments on eighteen benchmarking time series datasets, comparing them with state-of-the-art MTS clustering methods.

State-of-the-art Entity Matching (EM) approaches rely on transformer architectures, such as BERT , for generating highly contex-tualized embeddings of terms. The embeddings are then used to predict whether pairs of entity descriptions refer to the same real-world entity. BERT-based EM models demonstrated to be effective, but act as black-boxes for the users, who have limited insight into the motivations behind their decisions. In this paper, we perform a multi-facet analysis of the components of pre-trained and fine-tuned BERT architectures applied to an EM task. The main findings resulting from our extensive experimental evaluation are (1) the fine-tuning process applied to the EM task mainly modifies the last layers of the BERT components, but in a different way on tokens belonging to descriptions of matching / non-matching entities; (2) the special structure of the EM datasets, where records are pairs of entity descriptions is recognized by BERT; (3) the pair-wise semantic similarity of tokens is not a key knowledge exploited by BERT-based EM models.

State-of-the-art approaches model Entity Matching (EM) as a binary classification problem, where Machine (ML) or Deep Learning (DL) based techniques are applied to evaluate if descriptions of pairs of entities refer to the same real-world instance. Despite these approaches have experimentally demonstrated to achieve high effectiveness, their adoption in real scenarios is limited by the lack of interpretability of their behavior.

The state of the art approaches for performing Entity Matching (EM) rely on machine & deep learning models for inferring pairs of matching / non-matching entities.Although the experimental evaluations demonstrate that these approaches are effective, their adoption in real scenarios is limited by the fact that they are difficult to interpret.Explainable AI systems have been recently proposed for complementing deep learning approaches.Their application to the scenario offered by EM is still new and requires to address the specificity of this task, characterized by particular dataset schemas, describing a pair of entities, and imbalanced classes.This paper introduces Landmark Explanation, a generic and extensible framework that extends the capabilities of a post-hoc perturbation-based explainer over the EM scenario.Landmark Explanation generates perturbations that take advantage of the particular schemas of the EM datasets, thus generating explanations more accurate and more interesting for the users than the ones generated by competing approaches.

The paper studies the application of automated machine learning approaches (AutoML) for addressing the problem of Entity Matching (EM).This would make the existing, highly effective, Machine Learning (ML) and Deep Learning based approaches for EM usable also by non-expert users, who do not have the expertise to train and tune such complex systems.Our experiments show that the direct application of AutoML systems to this scenario does not provide high quality results.To address this issue, we introduce a new component, the EM adapter, to be pipelined with standard AutoML systems, that preprocesses the EM datasets to make them usable by automated approaches.The experimental evaluation shows that our proposal obtains the same effectiveness as the state-of-the-art EM systems, but it does not require any skill on ML to tune it. INTRODUCTIONMachine Learning (ML) has significantly advanced over the past ten years [1].On one side, the research on Big Data let emerge new challenges and made available scenarios and datasets where to experiment and improve ML techniques.On the other side, the increase of computer processing power, thanks in particular to the use of graphic processing units, enabled ML approaches running in commodity hardware.This led to the development of new ML algorithms and their implementations through frameworks and libraries is extensive and growing [17].Thus the ML technology moved from an R&D phase, for the exclusive use of specialized laboratories, to a mature phase where it can be adopted in business applications.Mature technologies have to be easy to use for both nonexperts and professionals.One of the main bottlenecks towards a large use of the ML technology is related to the configuration of the systems, where experts are typically needed to set the large number of hyper-parameters.Furthermore, the selection of the algorithm that best performs in a given ML task is based on an experimental evaluation in which the performances of competing approaches are compared.This requires a time-consuming and expensive iterative process in which multiple alternative solutions are tested until an optimal result is achieved.To address these issues, automated machine learning (AutoML) tools have been proposed.These are user-friendly and easy-touse systems that provide a unified interface for the automatic selection of the most appropriate ML model/algorithm for a given task and its automatic configuration.Some examples are Auto-WEKA [12], AutoSklearn [9], AutoGluon [8], Auto-Keras [11], H20 AutoML [10], and many other.This paper analyzes the application of AutoML systems to Entity Matching (EM), i.e. the task of identifying which records in a dataset refer to the same real-world entity [5].Applications

Inference of Machine Learning (ML) models, i.e. the process of obtaining predictions from trained models, is often an overlooked problem. Model inference is however one of the main contributors of both technical debt in ML applications and infrastructure complexity. MASQ is a framework able to run inference of ML models directly on DBMSs. MASQ not only averts expensive data movements for those predictive scenarios where data resides on a database, but it also naturally exploits all the "Enterprise-grade" features such as governance, security and auditability which make DBMSs the cornerstone of many businesses. MASQ compiles trained models and ML pipelines implemented in scikit-learn directly into standard SQL: no UDFs nor vendor-specific syntax are used, and therefore queries can be readily executed on any DBMS. In this demo, we will showcase MASQ's capabilities through a GUI allowing attendees to: (1) train ML pipelines composed of data featurizers and ML models; (2) compile the trained pipelines into SQL, and deploy them on different DBMSs (MySQL and SQLServer in the demo); and (3) compare the related performance under different configurations (e.g., the original pipeline on the ML framework against the SQL implementations).

Evaluation of the quality of data integration processes is usually performed via manual onerous data inspections. This task is particularly heavy in real business scenarios, where the large amount of data makes checking all the tuples infeasible and the frequent updates, i.e. changes in the sources and/or new sources, impose to repeat the evaluation over and over. Our idea is to address this issue by providing the experts with an unsupervised measure, based on word frequencies, which quantifies how much a dataset is representative of another dataset, giving an indication of how good is the integration process and whether deviations are happening and a manual inspection is needed. We also conducted some preliminary experiments, using shared datasets, that show the effectiveness of the proposed measures in typical data integration scenarios.

A rule-based entity matching task requires the definition of an effective set of rules, which is a time-consuming and error-prone process. The typical approach adopted for its resolution is a trial and error method, where the rules are incrementally added and modified until satisfactory results are obtained. This approach requires significant human intervention, since a typical dataset needs the definition of a large number of rules and possible interconnections that cannot be manually managed. In this paper, we propose TuneR, a software library supporting developers (i.e., coders, scientists, and domain experts) in tuning sets of matching rules. It aims to reduce human intervention by offering a tool for the optimization of rule sets based on user-defined criteria (such as effectiveness, interpretability, etc.). Our goal is to integrate the framework in the Magellan ecosystem, thus completing the functionalities required by the developers for performing Entity Matching tasks.

Many data analysis and knowledge mining tasks require a basic understanding of the content of a dataset prior to any data access. In this demo, we showcase how data descriptions---a set of compact, readable and insightful formulas of boolean predicates---can be used to guide users in understanding datasets. Finding the best description for a dataset is, unfortunately, both computationally hard and task-specific. This demo shows that not only we can generate descriptions at interactive speed, but also that diverse user needs---from anomaly detection to data exploration---can be accommodated through a user-driven process exploiting dynamic programming in concert with a set of heuristics.

We showcase QUEST (QUEry generator for STructured sources), a search engine for relational databases that combines semantic and machine learning techniques for transforming keyword queries into meaningful SQL queries. The search engine relies on two approaches: the forward, providing mappings of keywords into database terms (names of tables and attributes, and domains of attributes), and the backward, computing the paths joining the data structures identified in the forward step. The results provided by the two approaches are combined within a probabilistic framework based on the Dempster-Shafer Theory. We demonstrate QUEST capabilities, and we show how, thanks to the flexibility obtained by the probabilistic combination of different techniques, QUEST is able to compute high quality results even with few training data and/or with hidden data sources such as those found in the Deep Web.

Hidden Markov Models (HMMs) are today employed in a variety of applications, ranging from speech recognition to bioinformatics. In this paper, we present the List Viterbi training algorithm, a version of the Expectation-Maximization (EM) algorithm based on the List Viterbi algorithm instead of the commonly used forward-backward algorithm. We developed the batch and online versions of the algorithm, and we also describe an interesting application in the context of keyword search over databases, where we exploit a HMM for matching keywords into database terms. In our experiments we tested the online version of the training algorithm in a semi-supervised setting that allows us to take into account the feedbacks provided by the users.

Keyword queries offer a convenient alternative to traditional SQL in querying relational databases with large, often unknown, schemas and instances. The challenge in answering such queries is to discover their intended semantics, construct the SQL queries that describe them and used them to retrieve the respective tuples. Existing approaches typically rely on indices built a-priori on the database content. This seriously limits their applicability if a-priori access to the database content is not possible. Examples include the on-line databases accessed through web interface, or the sources in information integration systems that operate behind wrappers with specific query capabilities. Furthermore, existing literature has not studied to its full extend the inter-dependencies across the ways the different keywords are mapped into the database values and schema elements. In this work, we describe a novel technique for translating keyword queries into SQL based on the Munkres (a.k.a. Hungarian) algorithm. Our approach not only tackles the above two limitations, but it offers significant improvements in the identification of the semantically meaningful SQL queries that describe the intended keyword query semantics. We provide details of the technique implementation and an extensive experimental evaluation.

We propose the demonstration of Keymantic , a system for keyword-based searching in relational databases that does not require a-priori knowledge of instances held in a database. It finds numerous applications in situations where traditional keyword-based searching techniques are inapplicable due to the unavailability of the database contents for the construction of the required indexes.

In this article, we present MELIS (Meaning Elicitation and Lexical Integration System), a method and a software tool for enabling an incremental process of automatic annotation of local schemas (e.g. relational database schemas, directory trees) with lexical information. The distinguishing and original feature of MELIS is the incremental process: the higher the number of schemas which are processed, the more background/ domain knowledge is cumulated in the system (a portion of domain ontology is learned at every step), the better the performance of the systems on annotating new schemas. MELIS has been tested as a component of the MOMIS-Ontology Builder, a framework able to create a domain ontology representing a set of selected data sources, described with a standard W3C language wherein concepts and attributes are annotated according to the lexical reference database. We describe the MELIS component within the MOMIS-Ontology Builder framework and provide some experimental results of MELIS as a standalone tool and as a component integrated in MOMIS.

The increasing of globalization and flexibility required to the companies has generated, in the last decade, new issues, related to the managing of large scale projects within geographically distributed networks and to the cooperation of enterprises. ICT support systems are required to allow enterprises to share information, guarantee data-consistency and establish synchronized and collaborative processes. In this paper, we present a collaborative project management system that integrates data coming from aerospace industries with two main goals: avoiding inconsistencies generated by updates at the sources' level and minimizing data replications. The proposed system is composed of a collaborative project management component supported by a Web interface, a multiagent data integration component, which supports information sharing and querying, and SOAP enabled Web-services which ensure the whole interoperability of the software components. The system was developed by the University of Modena and Reggio Emilia, Gruppo Formula S.p.A. and Alenia Spazio S.p.A. within the EU WINK Project (Web-linked Integration of Network based Knowledge - IST-2000-28221).

Information overloading introduced by the large amount of data that is spread over the Internet must be faced in an appropriate way. The dynamism and the uncertainty of the Internet, along with the heterogeneity of the sources of information are the two main challenges for today's technologies related to information management. In the area of information integration, this paper proposes an approach based on mobile software agents integrated in the MOMIS (Mediator envirOnment for Multiple Information Sources) infrastructure, which enables semi-automatic information integration to deal with the integration and query of multiple, heterogeneous information sources (relational, object, XML and semi-structured sources). The exploitation of mobile agents in MOMIS can significantly increase the flexibility of the system. In fact, their characteristics of autonomy and adaptability well suit the distributed and open environments, such as the Internet. The aim of this paper is to show the advantages of the introduction in the MOMIS infrastructure of intelligent and mobile software agents for the autonomous management and coordination of integration and query processing over heterogeneous data sources.