arXiv subjects

Edgard Marx

Publications and source records attributed to Edgard Marx.

10 recordsLinked to original sources

arXiv2020

Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition

A booming amount of information is continuously added to the Internet as structured and unstructured data, feeding knowledge bases such as DBpedia and Wikidata with billions of statements describing millions of entities. The aim of Question Answering systems is to allow lay users to access such data using natural language without needing to write formal queries. However, users often submit questions that are complex and require a certain level of abstraction and reasoning to decompose them into basic graph patterns. In this short paper, we explore the use of architectures based on Neural Machine Translation called Neural SPARQL Machines to learn pattern compositions. We show that sequence-to-sequence models are a viable and promising option to transform long utterances into complex SPARQL queries.

cs.CL↗

arXiv2020

Where is Linked Data in Question Answering over Linked Data?

We argue that "Question Answering with Knowledge Base" and "Question Answering over Linked Data" are currently two instances of the same problem, despite one explicitly declares to deal with Linked Data. We point out the lack of existing methods to evaluate question answering on datasets which exploit external links to the rest of the cloud or share common schema. To this end, we propose the creation of new evaluation settings to leverage the advantages of the Semantic Web to achieve AI-complete question answering.

cs.CL↗

arXiv2018

Neural Machine Translation for Query Construction and Composition

Research on question answering with knowledge base has recently seen an increasing use of deep architectures. In this extended abstract, we study the application of the neural machine translation paradigm for question parsing. We employ a sequence-to-sequence model to learn graph patterns in the SPARQL graph query language and their compositions. Instead of inducing the programs through question-answer pairs, we expect a semi-supervised approach, where alignments between questions and queries are built through templates. We argue that the coverage of language utterances can be expanded using late notable works in natural language generation.

cs.CL↗

arXiv2018

Decentralized Collaborative Knowledge Management using Git

The World Wide Web and the Semantic Web are designed as a network of distributed services and datasets. The distributed character of the Web brings manifold collaborative possibilities to interchange data. The commonly adopted collaborative solutions for RDF data are centralized (e.g. SPARQL endpoints and wiki systems). But to support distributed collaboration, a system is needed, that supports divergence of datasets, brings the possibility to conflate diverged states, and allows distributed datasets to be synchronized. In this paper, we present Quit Store, it was inspired by and it builds upon the successful Git system. The approach is based on a formal expression of evolution and consolidation of distributed datasets. During the collaborative curation process, the system automatically versions the RDF dataset and tracks provenance information. It also provides support to branch, merge, and synchronize distributed RDF datasets. The merging process is guarded by specific merge strategies for RDF data. Finally, we use our reference implementation to show overall good performance and demonstrate the practical usability of the system.

cs.DB↗

arXiv2018

Expeditious Generation of Knowledge Graph Embeddings

Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space. Several approaches using embeddings have shown promising results on tasks such as link prediction, entity recommendation, question answering, and triplet classification. However, only a few methods can compute low-dimensional embeddings of very large knowledge bases without needing state-of-the-art computational resources. In this paper, we propose KG2Vec, a simple and fast approach to Knowledge Graph Embedding based on the skip-gram model. Instead of using a predefined scoring function, we learn it relying on Long Short-Term Memories. We show that our embeddings achieve results comparable with the most scalable approaches on knowledge graph completion as well as on a new metric. Yet, KG2Vec can embed large graphs in lesser time by processing more than 250 million triples in less than 7 hours on common hardware.

cs.CL↗

arXiv2018

Beyond Markov Logic: Efficient Mining of Prediction Rules in Large Graphs

Graph representations of large knowledge bases may comprise billions of edges. Usually built upon human-generated ontologies, several knowledge bases do not feature declared ontological rules and are far from being complete. Current rule mining approaches rely on schemata or store the graph in-memory, which can be unfeasible for large graphs. In this paper, we introduce HornConcerto, an algorithm to discover Horn clauses in large graphs without the need of a schema. Using a standard fact-based confidence score, we can mine close Horn rules having an arbitrary body size. We show that our method can outperform existing approaches in terms of runtime and memory consumption and mine high-quality rules for the link prediction task, achieving state-of-the-art results on a widely-used benchmark. Moreover, we find that rules alone can perform inference significantly faster than embedding-based methods and achieve accuracies on link prediction comparable to resource-demanding approaches such as Markov Logic Networks.

cs.DB↗

arXiv2017

Triple Scoring Using a Hybrid Fact Validation Approach - The Catsear Triple Scorer at WSDM Cup 2017

With the continuous increase of data daily published in knowledge bases across the Web, one of the main issues is regarding information relevance. In most knowledge bases, a triple (i.e., a statement composed by subject, predicate, and object) can be only true or false. However, triples can be assigned a score to have information sorted by relevance. In this work, we describe the participation of the Catsear team in the Triple Scoring Challenge at the WSDM Cup 2017. The Catsear approach scores triples by combining the answers coming from three different sources using a linear regression classifier. We show how our approach achieved an Accuracy2 value of 79.58% and the overall 4th place.

cs.IR↗

arXiv2017

Mandolin: A Knowledge Discovery Framework for the Web of Data

Markov Logic Networks join probabilistic modeling with first-order logic and have been shown to integrate well with the Semantic Web foundations. While several approaches have been devised to tackle the subproblems of rule mining, grounding, and inference, no comprehensive workflow has been proposed so far. In this paper, we fill this gap by introducing a framework called Mandolin, which implements a workflow for knowledge discovery specifically on RDF datasets. Our framework imports knowledge from referenced graphs, creates similarity relationships among similar literals, and relies on state-of-the-art techniques for rule mining, grounding, and inference computation. We show that our best configuration scales well and achieves at least comparable results with respect to other statistical-relational-learning algorithms on link prediction.

cs.DB↗

arXiv2017

SPARQL as a Foreign Language

In the last years, the Linked Data Cloud has achieved a size of more than 100 billion facts pertaining to a multitude of domains. However, accessing this information has been significantly challenging for lay users. Approaches to problems such as Question Answering on Linked Data and Link Discovery have notably played a role in increasing information access. These approaches are often based on handcrafted and/or statistical models derived from data observation. Recently, Deep Learning architectures based on Neural Networks called seq2seq have shown to achieve state-of-the-art results at translating sequences into sequences. In this direction, we propose Neural SPARQL Machines, end-to-end deep architectures to translate any natural language expression into sentences encoding SPARQL queries. Our preliminary results, restricted on selected DBpedia classes, show that Neural SPARQL Machines are a promising approach for Question Answering on Linked Data, as they can deal with known problems such as vocabulary mismatch and perform graph pattern composition.

cs.CL↗

arXiv2017

ROCKER: A Refinement Operator for Key Discovery

The Linked Data principles provide a decentral approach for publishing structured data in the RDF format on the Web. In contrast to structured data published in relational databases where a key is often provided explicitly, finding a set of properties that allows identifying a resource uniquely is a non-trivial task. Still, finding keys is of central importance for manifold applications such as resource deduplication, link discovery, logical data compression and data integration. In this paper, we address this research gap by specifying a refinement operator, dubbed ROCKER, which we prove to be finite, proper and non-redundant. We combine the theoretical characteristics of this operator with two monotonicities of keys to obtain a time-efficient approach for detecting keys, i.e., sets of properties that describe resources uniquely. We then utilize a hash index to compute the discriminability score efficiently. Therewith, we ensure that our approach can scale to very large knowledge bases. Results show that ROCKER yields more accurate results, has a comparable runtime, and consumes less memory w.r.t. existing state-of-the-art techniques.

cs.DB↗