Open Domain Question Answering over Knowledge Graphs Using Keyword Search, Answer Type Prediction, SPARQL and Pre-trained Neural Models

Nikas, Christos; Fafalios, Pavlos; Tzitzikas, Yannis

doi:10.1007/978-3-030-88361-4_14

Cited by 11 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, Semantic Web ontologies have become an indispensable technology for intelligent processing knowledge and provide a framework for conceptual models of shared domains. Domain knowledge can be used as a set of prior knowledge for constraints to help guide the search path and reduce search space, during the search and pattern generating process [10][11][12][13][14][15][16]. A set of preconstructed semantics-aware indexes were constructed [17].…”

Section: Overview and Related Workmentioning

confidence: 99%

A Two-Phase Method for Optimization of the SPARQL Query

Lin

Dong-yang²

2022

Journal of Sensors

View full text Add to dashboard Cite

With a rapid growth in the available resource description framework (RDF) data from disparate domains, the SPARQL query processing with graph structures has become increasingly important. In this pursuit, we designed a two-phase SPARQL query optimization method to process the SPARQL query. The structural characteristics of RDF data graphs, predicate path sequence indices (PPS-indices), were used to efficiently prune the search space, which captured the inherent features of the RDF data graphs, while the database is updated. Our storage model was based on a relational database. Compared to a baseline solution, the proposed method effectively reduced the cardinalities of the intermediate results during the query processing, and at least an order of magnitude improvement is achieved in filtering performance, thereby improving the efficiency of the query execution.

show abstract

Section: Overview and Related Workmentioning

confidence: 99%

A Two-Phase Method for Optimization of the SPARQL Query

Lin

Dong-yang²

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Therefore, instead of transforming a natural language question to am SPARQL query, one can apply various QA pipelines (see [73] for a survey), e.g., an alternative method is to transform the resulting CIDOC-CRM graph to natural text and to use existing BERT-based models for answering the question. Returning to our example, the approach presented in [74] (that relies on keyword search, SPARQL and pre-trained neural networks) can answer the above question (over the DBpedia dataset). In general, the more complex the question is the harder it is to answer it, especially in cases where one has to exploit various deductions from the knowledge graph.…”

Section: Example 4 Question Answeringmentioning

confidence: 99%

CIDOC-CRM and Machine Learning: A Survey and Future Research

et al. 2022

View full text Add to dashboard Cite

The CIDOC Conceptual Reference Model (CIDOC-CRM) is an ISO Standard ontology for the cultural domain that is used for enabling semantic interoperability between museums, libraries, archives and other cultural institutions. For leveraging CIDOC-CRM, several processes and tasks have to be carried out. It is therefore important to investigate to what extent we can automate these processes in order to facilitate interoperability. For this reason, in this paper, we describe the related tasks, and we survey recent works that apply machine learning (ML) techniques for reducing the costs related to CIDOC-CRM-based compliance and interoperability. In particular, we (a) analyze the main processes and tasks, (b) identify tasks where the recent advances of ML (including Deep Learning) would be beneficial, (c) identify cases where ML has been applied (and the results are successful/promising) and (d) suggest tasks that can benefit from applying ML. Finally, since the approaches that leverage both CIDOC-CRM data and ML are few in number, (e) we introduce our vision for the given topic, and (f) we provide a list of open CIDOC-CRM datasets that can be potentially used for ML tasks.

show abstract

“…As regards (c), there are several interactive information access systems, including browsing systems, such as [3,4,21] and also systems that can aid users that are not familiar with query languages to access the RDF knowledge base, for example, faceted search [6,7,13], interactive analytics services [22,23] and also systems for assisting the query building process, such as the system A-Qub [8]. Finally, regarding (d) Natural Language interface systems [24], where the input and output is given in natural language, and it returns short and precise answers, that is, through conversational access and Question Answering systems [25][26][27][28].…”

Section: Access Systems Over Rdfmentioning

confidence: 99%

RDFsim: Similarity-Based Browsing over DBpedia Using Embeddings

2021

View full text Add to dashboard Cite

Browsing has been the core access method for the Web from its beginning. Analogously, one good practice for publishing data on the Web is to support dereferenceable URIs, to also enable plain web browsing by users. The information about one URI is usually presented through HTML tables (such as DBpedia and Wikidata pages) and graph representations (by using tools such as LODLive and LODMilla). In most cases, for an entity, the user gets all triples that have that entity as subject or as object. However, sometimes the number of triples is numerous. To tackle this issue, and to reveal similarity (and thus facilitate browsing), in this article we introduce an interactive similarity-based browsing system, called RDFsim, that offers “Parallel Browsing”, that is, it enables the user to see and browse not only the original data of the entity in focus, but also the K most similar entities of the focal entity. The similarity of entities is founded on knowledge graph embeddings; however, the indexes that we introduce for enabling real-time interaction do not depend on the particular method for computing similarity. We detail an implementation of the approach over specific subsets of DBpedia (movies, philosophers and others) and we showcase the benefits of the approach. Finally, we report detailed performance results and we describe several use cases of RDFsim.

show abstract

Open Domain Question Answering over Knowledge Graphs Using Keyword Search, Answer Type Prediction, SPARQL and Pre-trained Neural Models

Cited by 11 publications

References 15 publications

A Two-Phase Method for Optimization of the SPARQL Query

A Two-Phase Method for Optimization of the SPARQL Query

CIDOC-CRM and Machine Learning: A Survey and Future Research

RDFsim: Similarity-Based Browsing over DBpedia Using Embeddings

Contact Info

Product

Resources

About