Natural Language Interfaces to Ontologies: Combining Syntactic Analysis and Ontology-Based Lookup through the User Interaction

Damljanović, Danica; Agatonović, Milan; Cunningham, Hamish

doi:10.1007/978-3-642-13486-9_8

Cited by 132 publications

(106 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In that field we have selected three QA systems: PowerAqua [16], FREyA (Feedback, Refinement and Extended VocabularY Aggregation) [9] and Treo [12], which share with our approach some similarities.…”

Section: Discussionmentioning

confidence: 99%

“…PowerAqua takes as input a natural language query, translates it into a set of logical queries, which are then answered by consulting and aggregating information derived from multiple heterogeneous semantic sources [9]. It is divided in three components: the Linguistic Component, the Relation Similarities Services and the Inference Engine.…”

Section: Discussionmentioning

confidence: 99%

“…When the predicate used in the question is not a copular verb, we come up with different schemes, as for instance in: (9).…”

Section: Pred Not [Be]mentioning

confidence: 99%

See 2 more Smart Citations

From Logical Forms to SPARQL Query with GETARUNS

Tripodi

Delmonte

2013

New Challenges in Distributed Information Filtering and Retrieval

View full text Add to dashboard Cite

Abstract. We present a system for Question Answering which computes a prospective answer from Logical Forms produced by a full-fledged NLP for text understanding, and then maps the result onto schemata in SPARQL to be used for accessing the Semantic Web. As an intermediate step, and whenever there are complex concepts to be mapped, the system looks for a corresponding amalgam in YAGO classes. It is just by the internal structure of the Logical Form that we are able to produce a suitable and meaningful context for concept disambiguation. Logical Forms are the final output of a complex system for text understanding -GETARUNS -which can deal with different levels of syntactic and semantic ambiguity in the generation of a final structure, by accessing computational lexical equipped with sub-categorization frames and appropriate selectional restrictions applied to the attachment of complements and adjuncts. The system also produces pronominal binding and instantiates the implicit arguments, if needed, in order to complete the required Predicate Argument structure which is licensed by the semantic component.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

From Logical Forms to SPARQL Query with GETARUNS

Tripodi

Delmonte

2013

New Challenges in Distributed Information Filtering and Retrieval

View full text Add to dashboard Cite

show abstract

“…But despite growing interest, there is a lack of standardized evaluation benchmarks to evaluate and compare the quality and performance of ontology-based question answering approaches at large scale [28]. To assess their current strengths and weaknesses, a range of such systems, for example GINGSENG [4], NLPReduce [23], Querix [21], FREyA [13] and PANTO [41], made use of the independent Mooney datasets 4 and corresponding queries. These are the only shared datasets that have been used to objectively 5 compare different ontology-based question answering systems for a given ontology or dataset.…”

Section: Existing Evaluation Methods and Competitionsmentioning

confidence: 99%

“…Recall, on the other hand, is defined differently among systems. Damljanovic et al [13] define recall as the ratio of the number of questions correctly answered by the system to the total number of all questions in the dataset, while for Wang et al [41] recall is the ratio of the number of questions that deliver some output-independently of whether the output is valid or not-to the total number of all questions. Such differences, together with discrepancies in the number of queries evaluated, render a direct comparison difficult.…”

Section: Existing Evaluation Methods and Competitionsmentioning

confidence: 99%

Evaluating question answering over linked data

López¹,

Unger

Cimiano

et al. 2013

Journal of Web Semantics

155

View full text Add to dashboard Cite

The availability of large amounts of open, distributed and structured semantic data on the web has no precedent in the history of computer science. In recent years, there have been important advances in semantic search and question answering over RDF data. In particular, natural language interfaces to online semantic data have the advantage that they can exploit the expressive power of Semantic Web data models and query languages, while at the same time hiding their complexity from the user. However, despite the increasing interest in this area, there are no evaluations so far that systematically evaluate this kind of systems, in contrast to traditional question answering and search interfaces to document spaces. To address this gap, we have set up a series of evaluation challenges for question answering over linked data. The main goal of the challenge was to get insight into the strengths, capabilities and current shortcomings of question answering systems as interfaces to query linked data sources, as well as benchmarking how these interaction paradigms can deal with the fact that the amount of RDF data available on the web is very large and heterogeneous with respect to the vocabularies and schemas used. Here we report on the results from the first and second of such evaluation campaigns. We also discuss how the second evaluation addressed some of the issues and limitations which arose from the first one, as well as the open issues to be addressed in future competitions.

show abstract

The Approach to Extracting Semantic Trees from Texts to Build an Ontology from Wiki-Resources

Yarushkina

Filippov

Moshkin

et al. 2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

The article describes the developed method of extracting semantic trees from text resources. This method is based on the use of a sequence of linguistic algorithms in constructing a syntactic sentence tree. The basis of the developed method is the algorithm for translating syntax trees of text fragments into the structures of semantic trees using a set of rules. A formal model of the rules is presented. The resulting semantic trees can be combined into a domain ontology taking into account the built-in relations between objects in the wiki resource. An example of our approach is also presented.

show abstract

Natural Language Interfaces to Ontologies: Combining Syntactic Analysis and Ontology-Based Lookup through the User Interaction

Cited by 132 publications

References 15 publications

From Logical Forms to SPARQL Query with GETARUNS

From Logical Forms to SPARQL Query with GETARUNS

Evaluating question answering over linked data

The Approach to Extracting Semantic Trees from Texts to Build an Ontology from Wiki-Resources

Contact Info

Product

Resources

About