Scaling Up Question-Answering to Linked Data

Abstract

Abstract. Linked Data semantic sources, in particular DBpedia, can be used to answer many user queries. PowerAqua is an open multi-ontology Question Answering (QA) system for the Semantic Web (SW). However, the emergence of Linked Data, characterized by its openness, heterogeneity and scale, introduces a new dimension to the Semantic Web scenario, in which exploiting the relevant information to extract answers for Natural Language (NL) user queries is a major challenge. In this paper we discuss the issues and lessons learned from our experience of integrating PowerAqua as a front-end for DBpedia and a subset of Linked Data sources. As such, we go one step beyond the state of the art on end-users interfaces for Linked Data by introducing mapping and fusion techniques needed to translate a user query by means of multiple sources. Our first informal experiments probe whether, in fact, it is feasible to obtain answers to user queries by composing information across semantic sources and Linked Data, even in its current form, where the strength of Linked Data is more a by-product of its size than its quality. We believe our experiences can be extrapolated to a variety of end-user applications that wish to scale, open up, exploit and re-use what possibly is the greatest wealth of data about everything in the history of Artificial Intelligence.

From hyperlinks to Semantic Web properties using Open Knowledge Extraction

“…The implementation of more sophisticated approaches for aligning generated properties to existing vocabularies is part of future work. Relevant related work are ontology matching techniques such as [13] 24 is an aggregator of Linked Open vocabularies (including DBpedia), and provides services for accessing their data; -Never-Ending Language Learning (NELL) 25 [6] is a machine learning system that extracts structured data from unstructured Web pages and stores it in a knowledge base. It runs continuously since 2010.…”

“…[26], [30]), relation extraction exploiting Linked Data [46] [24], and question answering on linked data [25].…”

“…from DBpedia ontology), and use their extensional interpretation in data (e.g. DBpedia) to either link two entities recognized in some text (as in [46][24]), or to find an answer to a question, from which some entities have been recognized (as in [25]). Domain is therefore limited to the coverage of the vocabulary, and distant supervision is provided by the background knowledge (e.g.…”

Linguistic Modeling of Linked Open Data for Question Answering

“…FREyA [5] and PowerAqua [9,10] are both question answering systems that are to a certain degree independent of the underlying ontology schema. Both systems work on existing Linked Open Data as is and can be configured to use multiple ontologies.…”

Evaluating Question Answering Over Linked Data

“…First, they are large enough to raise scalability and heterogeneity issues [26], but not so large that indexing and the processing of queries using semantic technologies would require computational resources outside the scope of most research groups. Second, by using closed datasets we create controllable and reproducible settings in which all systems can be evaluated under the same conditions.…”