Question answering over knowledge graphs (KGQA) has evolved from simple single-fact questions to complex questions that require graph traversal and aggregation. We propose a novel approach for complex KGQA that uses unsupervised message passing, which propagates confidence scores obtained by parsing an input question and matching terms in the knowledge graph to a set of possible answers. First, we identify entity, relationship, and class names mentioned in a natural language question, and map these to their counterparts in the graph. Then, the confidence scores of these mappings propagate through the graph structure to locate the answer entities. Finally, these are aggregated depending on the identified question type.This approach can be efficiently implemented as a series of sparse matrix multiplications mimicking joins over small local subgraphs. Our evaluation results show that the proposed approach outperforms the state-of-the-art on the LC-QuAD benchmark. Moreover, we show that the performance of the approach depends only on the quality of the question interpretation results, i.e., given a correct relevance score distribution, our approach always produces a correct answer ranking. Our error analysis reveals correct answers missing from the benchmark dataset and inconsistencies in the DBpedia knowledge graph. Finally, we provide a comprehensive evaluation of the proposed approach accompanied with an ablation study and an error analysis, which showcase the pitfalls for each of the question answering components in more detail.
First of all, I am aware that I am writing here one of the most read messages of this thesis. Thus, I am using part of these lines to do a little warning; you won't find the algorithm or the mathematical expression to solve all your problems, you won't even find conscientious reflexions opening minds. This thesis is just a story of how I, with the priceless support of my supervisors, spotted an open problem and carried out a research leading to efficient solutions. Much like the movies, the plot is a passionate travel throughout some unexplored fields and includes a good deal of sacrifice, hard working and, finally, success once the work obtained acceptation by the scientific community. So these are the easiest acknowledgments I have ever written as I only have to list the main actors of this movie, of this research story. This thesis is almost exclusively due to Miguel A. Martínez-Prieto, Claudio Gutierrez and Mario Arias, who have been advisors, colleagues and friends. I could write two books as large as this one to describe our experiences together which are, now and forever, part of my life memories. Thanks to Pablo de la Fuente for the support, and also to a full list of characters who don't even realize to be part of the plot in some way:
This document presents MLIF (Multi Lingual Information Framework) [1], a high-level model for describing multilingual data across a wide range of possible applications in the translation/localization process within several multimedia domains (e.g. broadcasting interactive programs within a multilingual community).
The publication and interchange of RDF datasets online has experienced significant growth in recent years, promoted by different but complementary efforts, such as Linked Open Data, the Web of Things and RDF stream processing systems. However, the current Linked Data infrastructure does not cater for the storage and exchange of sensitive or private data. On the one hand, data publishers need means to limit access to confidential data (e.g. health, financial, personal, or other sensitive data). On the other hand, the infrastructure needs to compress RDF graphs in a manner that minimises the amount of data that is both stored and transferred over the wire. In this paper, we demonstrate how HDT-a compressed serialization format for RDF-can be extended to cater for supporting encryption. We propose a number of different graph partitioning strategies and discuss the benefits and tradeoffs of each approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.