A machine reader is a tool able to transform natural language text to formal structured knowledge so as the latter can be interpreted by machines, according to a shared semantics. FRED is a machine reader for the semantic web: its output is a RDF/OWL graph, whose design is based on frame semantics. Nevertheless, FRED's graph are domain and task independent making the tool suitable to be used as a semantic middleware for domain-or task-specific applications. To serve this purpose, it is available both as REST service and as Python library. This paper provides details about FRED's capabilities, design issues, implementation and evaluation.

No abstract

No abstract

No abstract

Range and k-nearest neighbor searching are core problems in pattern recognition. Given a database S of objects in a metric space M and a query object q in M, in a range searching problem the goal is to find the objects of S within some threshold distance to q, whereas in a k-nearest neighbor searching problem, the k elements of S closest to q must be produced. These problems can obviously be solved with a linear number of distance calculations, by comparing the query object against every object in the database. However, the goal is to solve such problems much faster. We combine and extend ideas from the M-Tree, the Multivantage Point structure, and the FQ-Tree to create a new structure in the "bisector tree" class, called the Antipole Tree. Bisection is based on the proximity to an "Antipole" pair of elements generated by a suitable linear randomized tournament. The final winners a; b of such a tournament are far enough apart to approximate the diameter of the splitting set. If distða; bÞ is larger than the chosen cluster diameter threshold, then the cluster is split. The proposed data structure is an indexing scheme suitable for (exact and approximate) best match searching on generic metric spaces. The Antipole Tree outperforms by a factor of approximately two existing structures such as List of Clusters, M-Trees, and others and, in many cases, it achieves better clustering properties.Index Terms-Indexing methods, similarity measures, information search and retrieval.

Scientific knowledge has been traditionally disseminated and preserved through research articles published in journals, conference proceedings, and online archives. However, this article-centric paradigm has been often criticized for not allowing to automatically process, categorize, and reason on this knowledge. An alternative vision is to generate a semantically rich and interlinked description of the content of research publications. In this paper, we present the Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically generated knowledge graph that describes 820K research entities. AI-KG includes about 14M RDF triples and 1.2M reified statements extracted from 333K research publications in the field of AI, and describes 5 types of entities (tasks, methods, metrics, materials, others) linked by 27 relations. AI-KG has been designed to support a variety of intelligent services for analyzing and making sense of research dynamics, supporting researchers in their daily job, and helping to inform decision-making in funding bodies and research policymakers. AI-KG has been generated by applying an automatic pipeline that extracts entities and relationships using three tools: DyGIE++, Stanford CoreNLP, and the CSO Classifier. It then integrates and filters the resulting triples using a combination of deep learning and semantic technologies in order to produce a high-quality knowledge graph. This pipeline was evaluated on a manually crafted gold standard, yielding competitive results. AI-KG is available under CC BY 4.0 and can be downloaded as a dump or queried via a SPARQL endpoint.

Real-world use of RDF requires the ability to transparently represent and explain metadata associated with RDF triples. For example, when RDF triples are extracted automatically by information extraction programs, there is a need to represent where the triples came from, what their temporal validity is, and how certain we are that the triple is correct. Today, there is no theoretically clean and practically scalable mechanism that spans these different needs - reification is the only solution propose to date, and its implementations have been ugly. In this paper, we present Annotated RDF (or aRDF for short) in which RDF triples are annotated by members of a partially ordered set (with bottom element) that can be selected in any way desired by the user. We present a formal declarative semantics (model theory) for annotated RDF and develop algorithms to check consistency of aRDF theories and to answer queries to aRDF theories. We show that annotated RDF supports users who need to think about the uncertainty, temporal aspects, and provenance of the RDF triples in an RDF database. We develop a prototype aRDF implementation and show that our algorithms work efficiently even on real world data sets containing over 10 million triples

Today, increasing numbers of people are interacting online and a lot of textual comments are being produced due to the explosion of online communication. However, a paramount inconvenience within online environments is that comments that are shared within digital platforms can hide hazards, such as fake news, insults, harassment, and, more in general, comments that may hurt someone’s feelings. In this scenario, the detection of this kind of toxicity has an important role to moderate online communication. Deep learning technologies have recently delivered impressive performance within Natural Language Processing applications encompassing Sentiment Analysis and emotion detection across numerous datasets. Such models do not need any pre-defined hand-picked features, but they learn sophisticated features from the input datasets by themselves. In such a domain, word embeddings have been widely used as a way of representing words in Sentiment Analysis tasks, proving to be very effective. Therefore, in this paper, we investigated the use of deep learning and word embeddings to detect six different types of toxicity within online comments. In doing so, the most suitable deep learning layers and state-of-the-art word embeddings for identifying toxicity are evaluated. The results suggest that Long-Short Term Memory layers in combination with mimicked word embeddings are a good choice for this task.