The need to reduce greenhouse gas emissions and promote energy efficiency is crucial to achieve the energy transition and sustainable development goals. The availability of tools that provide clear information on energy consumption plays a key role in this transition, enabling users to monitor, manage, and optimize their energy use. This process, commonly referred to as energy feedback or eco-feedback, involves delivering information regarding energy usage and potentially suggesting more sustainable practices. Within the range of available tools, conversational agents can represent a valuable channel to receive detailed information about energy consumption and tailored advice for improving energy efficiency. The aim of this article is thus to explore the application of conversational agents, focusing on eco-feedback, as these tools are primarily devised to foster user awareness of energy usage and enhance more participatory conservation strategies. To this end, we conducted a keyword-based search of major scientific article databases, applying strict criteria to select relevant studies. The results of the collection showed that there is a very diverse landscape with respect to this topic. The surveyed works exhibit a high versatility in feedback goals. Furthermore, while predominantly applied domestically, they also show potential in commercial and industrial settings. Implementation choices also vary to a great extent, while evaluation practices lack a systematic approach and highlight the need for greater consistency. In light of these remarks, we also outline possible future extensions of this type of application, exploring in particular the emerging challenges associated with the increased use of renewable sources and the rise of local decentralized energy communities.

In this paper we present QA3 , a question answering (QA) system over RDF data cubes. The system first tags chunks of text with elements of the knowledge base, and then leverages the well-defined structure of data cubes to create a SPARQL query from t

The hypernymy relation is the one occurring between an instance term and its general term (e.g., “lion” and “animal”, “Italy” and “country”). This paper we addresses Hypernym Discovery, the NLP task that aims at finding valid hypernyms from words in a given text, proposing HyperRank, an unsupervised approach that therefore does not require manually-labeled training sets as most approaches in the literature. The proposed algorithm exploits the cosine distance of points in the vector space of word embeddings, as already proposed by previous state of the art approaches, but the ranking is then corrected by also weighting word frequencies and the absolute level of similarity, which is expected to be similar when measuring co-hyponyms and their common hypernym. This brings us two major advantages over other approaches—(1) we correct the inadequacy of semantic similarity which is known to cause a significant performance drop and (2) we take into accounts multiple words if provided, allowing to find common hypernyms for a set of co-hyponyms—a task ignored in other systems but very useful when coupled with set expansion (that finds co-hyponyms automatically). We then evaluate HyperRank against the SemEval 2018 Hypernym Discovery task and show that, regardless of the language or domain, our algorithm significantly outperforms all the existing unsupervised algorithms and some supervised ones as well. We also evaluate the algorithm on a new dataset to measure the improvements when finding hypernyms for sets of words instead of singletons.