A Semantic Question Answering Framework for Large Data Sets

World Wide Web

The Semantic Web is gaining increasing interest to fulfill the need of sharing, retrieving, and reusing information. In this context, the Resource Description Framework (RDF) has been conceived to provide an easy way to represent any kind of data and metadata, according to a lightweight model and syntaxes for serialization (RDF/XML, N3, etc.). Despite RDF has the advantage of being general and simple, it cannot be used as a storage model as it is, since it can be easily shown that even simple management operations involve serious performance limitations. In this paper we present a framework which provides a flexible and persistent layer relying on a novel storage model that guarantees good scalability and performance of query evaluation. The approach is based on the notion of construct, that represents a concept of the domain of interest. This makes the approach easily extensible and independent from the specific knowledge representation language. Based on this representation, reasoning capabilities are supported by a rule-based engine. Finally we present experimental results over real world scenarios to demonstrate the feasibility of the approach.

As an increasing amount of RDF data is published as Linked Data, intuitive ways of accessing this data become more and more important. Question answering approaches have been proposed as a good compromise between intuitiveness and expressivity. Most question answering systems translate questions into triples which are matched against the RDF data to retrieve an answer, typically relying on some similarity metric. However, in many cases, triples do not represent a faithful representation of the semantic structure of the natural language question, with the result that more expressive queries can not be answered. To circumvent this problem, we present a novel approach that relies on a parse of the question to produce a SPARQL template that directly mirrors the internal structure of the question. This template is then instantiated using statistical entity identification and predicate detection. We show that this approach is competitive and discuss cases of questions that can be answered with our approach but not with competing approaches.

Question answering is the task of answering questions in natural language. Linked Data project and Semantic Web community made it possible for us to query structured knowledge bases like DBpedia and YAGO. Only expert users, however, with the knowledge of RDF and ontology definitions can build correct SPARQL queries for querying knowledge bases formally. In this paper, we present a method for mapping natural language questions to ontology-based structured queries to retrieve direct answers from open knowledge bases (linked data). Our tool is based on translating natural language questions into RDF triple patterns using the dependency tree of the question text. In addition, our method uses relational patterns extracted from the Web. We tested our tool using questions from QALD-2, Question Answering over Linked Data challenge track and found promising preliminary results.

2007

Abstract. Restriction to a predefined set of ontologies, and consequently limitation to specific domain environments is a pervading drawback in Semantic Search technologies. In this work we present PowerAqua [2], a multi-ontology-based Question Answering (QA) platform that exploits multiple distributed ontologies and knowledge bases to answer queries in multi-domain environments.

2013

Abstract. W3C currently extends the SPARQL query language with so-called entailment regimes, which define how queries are evaluated using logical entailment relations. We describe a sound and complete algorithm for the OWL Direct Semantics entailment regime. Since OWL’s Direct Semantics is based on Description Logics (DLs), this results in an expressive query language for DL knowledge bases. The query language differs from the commonly studied conjunctive queries in that it only has distinguished variables. Furthermore, variables can occur within complex concepts and can also bind to concept or role names. We provide a prototypical implementation and propose several novel optimization strategies. We evaluate the efficiency of the proposed optimizations and find that for ABox queries our system performs comparably to already deployed systems. For complex queries an improvement of up to three orders of magnitude can be observed. 1

2019

Chatbot is a conversational agent that communicates with users based on natural language. It is founded on a question answering system which tries to understand the intent of the user. Several chatbot methods deal with a model based template of question answering. However, these approaches are not able to cope with various questions and can affect the quality of the results. To address this issue, we propose a new semantic question answering approach combining Natural Language Processing (NLP) methods and Semantic Web techniques to analyze user's question and transform it into SPARQL query. An ontology has been developed to represent the domain knowledge of the chatbot. Experimentations show that our approach outperforms state of the art methods.

2011

W3C currently extends the SPARQL query language with so-called entailment regimes, which define how queries are evaluated using logical entailment relations. We describe a sound and complete algorithm for the OWL Direct Semantics entailment regime. Since OWL's Direct Semantics is based on Description Logics (DLs), this results in an expressive query language for DL knowledge bases. The query language differs from the commonly studied conjunctive queries in that it only has distinguished variables. Furthermore, variables can occur within complex concepts and can also bind to concept or role names. We provide a prototypical implementation and propose several novel optimizations strategies. We evaluate the efficiency of the proposed optimizations and find that for ABox queries our system performs comparably to already deployed systems. For complex queries an improvement of up to three orders of magnitude can be observed.

ABC Research Alert

As the amount of information in the world is growing very quickly, in the case of the semantic web this increasing amount of information is becoming more difficult to find and manage the exact answers to our various questions. To overcome these difficulties some systems have been developed that make it work for us. But there exists many challenges in developing these systems that require a lot of improvement. In this tutorial, we give a basic understanding of Semantic web, RDF triple, SPARQL query language. Here we will discuss the main obstacles for the QA system in processing the questions and a detailed survey of the existing systems. We also provide some advantages and disadvantages of existing QA systems. We also discuss the evaluation campaigns of the existing models based on their precision, recall and F-1 scores on the QALD dataset.

Communications in Computer and Information Science, 2018

Nowadays, we observe a rapid increase in the volume of RDF knowledge bases (KBs) and a need for functionalities that will help users access them in natural language without knowing the features of the KBs and structured query languages, such as SPARQL. This paper introduces Grammatical Question Answering (GQA), a system for answering questions in the English language over DBpedia, which involves parsing of questions by means of Grammatical Framework and further analysis of grammar components. We built an abstract conceptual grammar and a concrete English grammar, so that the system can handle complex syntactic constructions that are in the focus of the SQA2018 challenge. The parses are further analysed and transformed into SPARQL queries that can be used to retrieve the answers for the users' questions.

Lecture Notes in Computer Science, 2016

Natural Language Query Formalization involves semantically parsing queries in natural language and translating them into their corresponding formal representations. It is a key component for developing question-answering (QA) systems on RDF data. The chosen formal representation language in this case is often SPARQL. In this paper, we propose a framework, called AskNow, where users can pose queries in English to a target RDF knowledge base (e.g. DBpedia), which are first normalized into an intermediary canonical syntactic form, called Normalized Query Structure (NQS), and then translated into SPARQL queries. NQS facilitates the identification of the desire (or expected output information) and the user-provided input information, and establishing their mutual semantic relationship. At the same time, it is sufficiently adaptive to query paraphrasing. We have empirically evaluated the framework with respect to the syntactic robustness of NQS and semantic accuracy of the SPARQL translator on standard benchmark datasets.