Article R2D2: A Dbpedia Using Triple-Pattern Like Queries

Haridimos Kondylakis 1,2,* , Dimitrios Tsirigotakis 1, Giorgos Fragkiadakis 1, Emmanouela Panteri 1, Alexandros Papadakis 1, Alexandros Fragkakis 1, Eleytherios Tzagkarakis 1, Ioannis Rallis 1, Zacharias Saridakis 1, Apostolos Trampas 1, Giorgos Pirounakis 1 and Nikolaos Papadakis 1

1 Department of Electrical and Computer Engineering, Hellenic Mediterranean University, 71004 Heraklion, Greece; [email protected] (D.T.); [email protected] (G.F.); [email protected] (E.P.); [email protected] (A.P.); [email protected] (A.F.); [email protected] (E.T.); rallis@staff.teicrete.gr (I.R.); [email protected] (Z.S.); [email protected] (A.T.); [email protected] (G.P.); [email protected] (N.P.) 2 Institute of , FORTH, N. Plastira 100, 71500 Heraklion, Greece * Correspondence: [email protected]; Tel.: +30-2810-391449

 Received: 21 June 2020; Accepted: 1 September 2020; Published: 3 September 2020 

Abstract: , also known as conversation agents, are programs that are able to simulate and reproduce an intelligent conversation with humans. Although this type of program is not new, the explosion of the available information and the rapid increase of the users seeking this information have renewed the interest in their development. In this paper, we present R2D2, an intelligent chatbot relying on technologies and offering an intelligent controlled natural language interface for accessing the information available in DBpedia. The chatbot accepts structured input, allowing users to enter triple-pattern like queries, which are answered by the underlying engine. While typing, an auto-complete service guides users on creating the triple patterns, suggesting resources available in the DBpedia. Based on user input (in the form of triple-pattern like queries), the corresponding SPARQL queries are automatically formulated. The queries are submitted to the corresponding DBpedia SPARQL endpoint, and then the result is received by R2D2 and augmented with maps and visuals and eventually presented to the user. The usability evaluation performed shows the advantages of our solution and its usefulness.

Keywords: chatbots; DBpedia; conversation agents

1. Introduction During the last years, chatbots have played a prominent role as human–computer interfaces. Chatbots are computer programs that are capable of establishing a conversation with users, with either written or vocal commands. Such programs provide easy and pleasant conversations and answers; they can automatically manage large volumes of users, replacing human operators, which are not always available [1]. The first chatbot was ELIZA [2], trying to simulate a psychotherapist, whereas many chatbots are currently promoted and used by commercial vendors such as Apple’s Siri, Alexa, Microsoft Cortana, and Google Assistant [3], whereas it is foreseen that between 2017 and 2023, the spread of chatbots will be increased up to 37% [1]. In addition, although a vast amount of information is now available online, still, users find it difficult to identify the information of interest and navigate to the numerous and large information sources [4,5]. DBpedia [6] is a crowd-sourced community effort, including 38.4 million resources in multiple languages, trying to extract structured content from the information already available in various

Algorithms 2020, 13, 217; doi:10.3390/a13090217 www.mdpi.com/journal/algorithms Algorithms 2020, 13, 217 2 of 13

Wikimedia projects. Data are available as Linked , and on