Search

There is a recent trend for using the novel Artificial Intelligence ChatGPT chatbox, which provides detailed responses and articulate answers across many domains of knowledge. However, in many cases it returns plausible-sounding but incorrect or inaccurate responses, whereas it does not provide evidence. Therefore, any user has to further search for checking the accuracy of the answer or/and for finding more information about the entities of the response. At the same time there is a high proliferation of RDF Knowledge Graphs (KGs) over any real domain, that offer high quality structured data. For enabling the combination of ChatGPT and RDF KGs, we present a research prototype, called GPToLODS, which is able to enrich any ChatGPT response with more information from hundreds of RDF KGs. In particular, it identifies and annotates each entity of the response with statistics and hyperlinks to LODsyndesis KG (which contains integrated data from 400 RDF KGs and over 412 million entities). In this way, it is feasible to enrich the content of entities and to perform fact checking and validation for the facts of the response at real time.

An increasing number of organisations in almost all fields have started adopting semantic web technologies for publishing their data as open, linked and interoperable (RDF) datasets, queryable through the SPARQL language and protocol. Link traversal has emerged as a SPARQL query processing method that exploits the Linked Data principles and the dynamic nature of the Web to dynamically discover data relevant for answering a query by resolving online resources (URIs) during query evaluation. However, the execution time of link traversal queries can become prohibitively high for certain query types due to the high number of resources that need to be accessed during query execution. In this paper we propose and evaluate baseline methods for estimating the evaluation cost of link traversal queries. Such methods can be very useful for deciding on-the-fly the query execution strategy to follow for a given query, thereby reducing the load of a SPARQL endpoint and increasing the overall reliability of the query service. To evaluate the performance of the proposed methods, we have created (and make publicly available) a ground truth dataset consisting of 2,425 queries.

A vast area of research in historical science concerns the documentation and study of artefacts and related evidence. Current practice mostly uses spreadsheets or simple relational databases to organise the information as rows with multiple columns of related attributes. This form offers itself for data analysis and scholarly interpretation, however it also poses problems including i) the difficulty for collaborative but controlled documentation by a large number of users, ii) the lack of representation of the details from which the documented relations are inferred, iii) the difficulty to extend the underlying data structures as well as to combine and integrate data from multiple and diverse information sources, and iv) the limitation to reuse the data beyond the context of a particular research activity. To support historians to cope with these problems, in this paper we describe the Synthesis documentation system and its use by a large number of historians in the context of an ongoing research project in the field of History of Art. The system is Web-based and collaborative, and makes use of existing standards for information documentation and publication (CIDOC-CRM, RDF), focusing on semantic interoperability and the production of data of high value and long-term validity., Comment: This is a preprint of an article accepted for publication at the 20th International Semantic Web Conference (ISWC 2021)

Question Answering (QA) is a challenging topic since it requires tackling the various difficulties of natural language understanding. Since evaluation is important not only for identifying the strong and weak points of the various techniques for QA, but also for facilitating the inception of new methods and techniques, in this paper we present a collection for evaluating QA methods over free text that we have created. Although it is a small collection, it contains cases of increasing difficulty, therefore it has an educational value and it can be used for rapid evaluation of QA systems., Comment: 13 pages

In this work we discuss the related challenges and describe an approach towards the fusion of state-of-the-art technologies from the Spoken Dialogue Systems (SDS) and the Semantic Web and Information Retrieval domains. We envision a dialogue system named LD-SDS that will support advanced, expressive, and engaging user requests, over multiple, complex, rich, and open-domain data sources that will leverage the wealth of the available Linked Data. Specifically, we focus on: a) improving the identification, disambiguation and linking of entities occurring in data sources and user input; b) offering advanced query services for exploiting the semantics of the data, with reasoning and exploratory capabilities; and c) expanding the typical information seeking dialogue model (slot filling) to better reflect real-world conversational search scenarios., Comment: Presented in Search Oriented Conversational AI SCAI 17 Workshop, Co-located with ICTIR 17, 2017

In this paper we introduce a method for exploiting entities from the emerging Web of Data for enhancing various Information Retrieval (IR) services. The approach is based on named-entity recognition applied in a set of search results, and on a graph of documents and identified entities that is constructed dynamically and analyzed stochastically using a Random Walk method. The result of this analysis is exploited in two different contexts: for automatic query expansion and for re-ranking a set of retrieved results. Evaluation results in the 2015 TREC Clinical Decision Support Track illustrate that query expansion can increase recall by retrieving more relevant hits, while re-ranking can notably improve the ranked list of results by moving relevant but low-ranked hits in higher positions.

This paper introduces a simple method for producing multichannel MIDI music that is based on randomness and simple probabilities. One distinctive feature of the method is that it produces and sends in parallel to the sound card more than one unsynchronized channels by exploiting the multi-threading capabilities of general purpose programming languages. As consequence the derived sound offers a quite ``full" and ``unpredictable" acoustic experience to the listener. Subsequently the paper reports the results of an evaluation with users. The results were very surprising: the majority of users responded that they could tolerate this music in various occasions., Comment: 7 pages, 5 figures

A user consultation exercise has been conducted to identify current practices with respect to long-term data preservation within the earth science domain. This survey has been conducted as two separate but related tasks and covered a wide range of topics including semantics, metadata, ontologies, policies and technologies. This report contains the results of the direct user consultations and also includes information from a web-based independent search activity. It will be used as input to work package (WP) 33 which is concerned with the definition of data preservation policies and harmonised semantics, ontologies and metadata as well as the development of a preliminary architecture for a European earth science long-term data preservation infrastructure.

Even though library and archival practice, as well as Digital Preservation, have a long tradition in identifying information objects, the question of their precise identity under change of carrier or migration is still a riddle to science. The objective of this paper is to provide criteria for the unique identification of some important kinds of information objects, independent from the kind of carrier or specific encoding. Our approach is based on the idea that the substance of some kinds of information objects can completely be described in terms of discrete arrangements of finite numbers of known kinds of symbols, such as those implied by style guides for scientific journal submissions. Our theory is also useful for selecting or describing what has to be preserved. This is a fundamental problem since curators and archivists would like to formally record the decisions of what has to be preserved over time and to decide (or verify) whether a migration (transformation) preserves the intended information content. Furthermore, it is important for reasoning about the authenticity of digital objects, as well as for reducing the cost of digital preservation., Comment: 30 pages, 10 figures. Comparison to the previous version: Improved use of language

An increasing amount of data is published on the Web according to the Linked Open Data (LOD) principles. End users would like to browse these data in a flexible manner. In this paper we focus on similarity-based browsing and we introduce a novel method for computing the similarity between two entities of a given RDF/S graph. The distinctive characteristics of the proposed metric is that it is generic (it can be used to compare nodes of any kind), it takes into account the neighborhoods of the nodes, and it is configurable (with respect to the accuracy vs computational complexity tradeoff). We demonstrate the behavior of the metric using examples from an application over LOD. Finally, we generalize and elaborate on implementation approaches harmonized with the distributed nature of LOD which can be used for computing the most similar entities using neighborhood-based similarity metrics.

One of the distinctive features of Information Retrieval systems comparing to Database Management systems, is that they offer better compression for posting lists, resulting in better I/O performance and thus faster query evaluation. In this paper, we introduce database representations of the index that reduce the size (and thus the disk I/Os) of the posting lists. This is not achieved by redesigning the DBMS, but by exploiting the non 1NF features that existing Object-Relational DBM systems (ORDBMS) already offer. Specifically, four different database representations are described and detailed experimental results for one million pages are reported. Three of these representations are one order of magnitude more space efficient and faster (in query evaluation) than the plain relational representation.