Natural Language Query Interface Research Articles

Evaluation of Criteria2Query: Towards Augmented Intelligence for Cohort Identification.

Electronic healthcare records data promises to improve the efficiency of patient eligibility screening, which is an important factor in the success of clinical trials and observational studies. To bridge the sociotechnical gap in cohort identification by end-users, who are clinicians or researchers unfamiliar with underlying EHR databases, we previously developed a natural language query interface named Criteria2Query (C2Q) that automatically transforms free-text eligibility criteria to executable database queries. In this study, we present a comprehensive evaluation of C2Q to generate more actionable insights to inform the design and evaluation of future natural language user interfaces for clinical databases, towards the realization of Augmented Intelligence (AI) for clinical cohort definition via e-screening.

Building a Natural Language Query and Control Interface for IoT Platforms

The rapid development and popularity of IoT technology has reshaped the way people interact with the real world. Many researchers have attempted to build natural language interfaces for IoT platforms, but have not produced much progress in parsing natural language commands that contain multiple operations and more complex logical structures. In this paper, we propose IoT-NLI, a natural language query and control interface for popular IoT platforms, which uses hierarchical semantic parsing algorithms and directed edge-tagged graph structures to efficiently parse natural language commands input by users, enabling them to perform multiple operations contained in one complex natural language command. Experiments in three domains, agriculture, industry, and smart home, show that IoT-NLI has excellent performance and reasonable response time. Finally, a IoT-NLI application was developed on the Android platform and integrated with the AliCloud platform. It enables users to query and control devices on Android phones through chat windows similar to instant messaging software.

SCADA-NLI: A Natural Language Query and Control Interface for Distributed Systems

Human–Computer natural language interaction is helpful to reduce the operation and maintenance cost of the SCADA system, and it is necessary to solve the complex natural language interface problem that supports data query and real-time control. According to the complexity of natural language instructions, a hierarchical classification of semantic parsing algorithm is adopted. Firstly, the KWECS method is used to classify the intent of natural language instruction, then the TF-IDF keyword extraction algorithm combined with the cosine similarity is used to structure the key-value of the classified natural language instructions which was used into SCADA control intermediate language and then formally converted into actual control or query instruction. If the analysis fails, the complex control and query instruction analysis are carried out according to the classification results, structuring instruction parsing based on dependency parsing and SQL natural language parsing based on deep learning are adopted respectively to implement real-time control interface and database query interface. Our experimental results show that the proposed hierarchical classification of natural language comprehensive query and control interface can better solve the problem of human-computer natural language interaction in the SCADA system, and the accuracy of intent recognition reaches 96.5%. In more detail, the accuracy, precision, recall, and F-score of instruction parsing reach 88.47%, 90.21%, 89.48%, and 89.72% respectively. Especially, it provides more convenient interactive means for industrial and agricultural information management and control.

Modelling and Designing of NLP Interface to Database for Afaan Oromoo

Database management system has been widely used for storing and retrieving data. However, database is often hard to access the data since their interface is rigid in cooperating with user, due to that analysis of natural language query interface to relational databases has gained much interest in research community. This can be termed as structured free query interface as it allows the users to retrieve the data from the database without knowing the underlying schema. Structured free query interface should address majorly two problems. Querying the system with natural language interfaces is comfortable for the naive users but it is difficult for the machine to understand. The other problem is that the users can query the system with different expressions to retrieve the same information. The different words used in the query can have same meaning and the same word can have multiple meanings. Hence; it is the responsibilities of the NLI to understand the exact meaning of the word in the particular context to handle such problem the researcher develops an algorithm that is from manually crafted rule that extracted from user queries for proper query translation and SQL query generation. The proposed, pattern matching approach to natural language interface to database system has been passes through various phases. The idea behind the approach is to overcome the problem bottleneck luck of tools in the language, while pattern-matching method can fill the gap of those resources. This makes our approach suitable for AONIDB since Afaan Oromoo is under resourced language. The exact meaning of the word used in the query in particular context obtained using domain-mapping dictionary and database-mapping table constructed form student database that contains grade, department and course table for mapping database information with the help of an algorithm developed by researcher based on the rule that extracted from collected user query. The system has been developed in which user can input query in Afaan Oromoo language and can see result in the same language. The proposed system can handle list query, single and multiple conditional queries, aggregate function queries and join queries. The proposed system evaluated on 100 Afaan Oromoo queries using student database with precision, recall and F-measure. The result of testing is very encouraging and an average performance of 94.2% that implies that the systems validity and reliability is very high, an indicator of its strong and successfully features use and operation. Yet; further experiments using different approaches that extend this work are needed for a better performance.

A linked data graph approach to integration of immunological data.

Systems biology involves the integration of multiple data types (across different data sources) to offer a more complete picture of the biological system being studied. While many existing biological databases are implemented using the traditional SQL (Structured Query Language) database technology, NoSQL database technologies have been explored as a more relationship-based, flexible and scalable method of data integration. In this paper, we describe how to use the Neo4J graph database to integrate a variety of types of data sets in the context of systems vaccinology. Specifically, we have converted into a common graph model diverse types of vaccine response measurement data from the NIH/NIAID ImmPort data repository, pathway data from Reactome, influenza virus strains from WHO, and taxonomic data from NCBI Taxon. While Neo4J provides a graph-based query language (Cypher) for data retrieval, we develop a web-based dashboard for users to easily browse and visualize data without the need to learn Cypher. In addition, we have prototyped a natural language query interface for users to interact with our system. In conclusion, we demonstrate the feasibility of using a graph-based database for storing and querying immunological data with complex biological relationships. Querying a graph database through such relationships has the potential to reveal novel relationships among heterogeneous biological data.

Towards Automating the Creation of OBDA Systems

In the paper, we consider automating the process of constructing and debugging ontology-based data access systems by using the information stored in external ontology resources. In particular, for the constructing stage, we propose to use a tool that suggests concepts from external repositories for those tables from a relational database, which haven’t been matched with concepts from a domain ontology by ontology alignment techniques. For the debugging stage, we show how a tool for navigation in a collection of ontologies can be used to simplify SPARQL query writing by generating lacking parts of query thus enhancing ontology engineer’s productivity. The proposed approaches have been implemented and used in our system, named Reply, which transforms traditional information systems into intelligent systems with a natural language query interface.

Understanding Natural Language Queries over Relational Databases

Natural language has been the holy grail of query interface designers, but has generally been considered too hard to work with, except in limited specific circumstances. In this paper, we describe the architecture of an interactive natural language query interface for relational databases. Through a carefully limited interaction with the user, we are able to correctly interpret complex natural language queries, in a generic manner across a range of domains. By these means, a logically complex English language sentence is correctly translated into a SQL query, which may include aggregation, nesting, and various types of joins, among other things, and can be evaluated against an RDBMS.We have constructed a\ system, NaLIR (Natural Language Interface for Relational databases), embodying these ideas. Our experimental assessment, through user studies, demonstrates that NaLIR is good enough to be usable in practice: even naive users are able to specify quite complex ad-hoc queries.

A Model of a Generic Natural Language Interface for Querying Database

Extracting information from database is typically done by using a structured language such as SQL (Structured Query Language). But non expert users can’t use this later. Wherefore using Natural Language (NL) for communicating with database can be a powerful tool. But without any help, computers can’t understand this language; that is why it is essential to develop an interface able to translate user’s query given in NL into an equivalent one in Database Query Language (DBQL). This paper presents a model of a generic natural language query interface for querying database. This model is based on machine learning approach which allows interface to automatically improve its knowledge base through experience. The advantage of this interface is that it functions independently of the database language, content and model. Experimentations are realized to study the performance of this interface and make necessary corrections for its amelioration

Ontology Based Natural Language Interface for Relational Databases

Developing Natural Language Query Interface to Relational Databases has gained much interest in research community since forty years. This can be termed as structured free query interface as it allows the users to retrieve the data from the database without knowing the underlying schema. Structured free query interface should address majorly two problems. Querying the system with Natural Language Interfaces (NLIs) is comfortable for the naive users but it is difficult for the machine to understand. The other problem is that the users can query the system with different expressions to retrieve the same information. The different words used in the query can have same meaning and also the same word can have multiple meanings. Hence it is the responsibility of the NLI to understand the exact meaning of the word in the particular context. In this paper, a generic NLI Database system has proposed which contains various phases. The exact meaning of the word used in the query in particular context is obtained using ontology constructed for customer database. The proposed system is evaluated using customer database with precision, recall and f1-measure.

The Amalgamation of NLP with TextCategorization

Text Mining (TM) and Natural Language Processing (NLP) are very closely related to each other. Though TM is not really associated with the semantic and the syntax of a language, it does try to link documents or unstructured data in such a way that at the end of the day we can say those documents are semantically closely associated. TM has a number of subtasks like Text Clustering, Text Summarizing, Text Categorizing, etc. In this paper we are discussing research related to converting a simple English language question to its equivalent Structured Query Language (SQL) statement for a novice to fetch information from a database. This tool that we have developed has been named the N-ELIDB – Natural English Language Query Interface to Database. This is a heuristic tool which after generating the SQL, tries to categorize the questions using the concept of Text Categorization. The previous part is for a normal user and the later part is for the Text Miner.

Research on Chinese Natural Language Query Interface to Database Based on Syntax and Semantic

The query of database must rely on professional query language, which is difficult to grasp for ordinary users. Natural language query interface (NLQI) can be applied to solve this problem with better human-computer interaction and intelligence. However, current natural language understanding technology is not mature. Though the query sentences’ structure is fixed, it is also difficult to accurately convert query sentences into understandable database query language for computer. Therefore a method of designing NLQI based on syntax and semantic analysis is proposed in this paper. First of all, Maximum forward and maximum reverse matching algorithms are used to analyse sentence by part of speech (POS) template, which is able to demonstrate the syntax relationship among the words. After syntax analysis, query conditions and targets are identified. Then, single conditions and targets are analyzed to relative standard forms by the relationship among entity, property, connect verb and unit. At last, these standard forms are transformed to SQL sentence. Regarding printing ERP system as experimental subject, experiment is done in this paper. The result shows that the method proposed in this paper can meet the needs of natural language query, and has a good transform effect for combination, omitting and other complex sentences.

Semantic Search based on Ontology Alignment for Information Retrieval

Traditional search is keyword based search and does not focus on relationship between the words. In semantic search, the search is performed on basis of the meaning of the terms and concepts. The semantics i.e. meaning is expressed through structured knowledge representation or Ontologies. Resource Description Framework (RDF) is used as the data model and SPARQL query language is used to query the RDF data. Currently, there is lot of RDF based data set, e.g. Dbpedia, Freebase, Geonames etc. Semantic search is gaining popularity in recent times. As systems cannot exist in isolation but need to interact with each other, complex systems may require integration of multiple systems. Semantic search systems may take input from heterogeneous systems, in which case, the common and shared entities have to be identified and mapped properly. Also, in semantic search, user has to enter query in formal query language SPARQL, which is quite difficult to learn and use for laymen. We are presenting herewith, an application in which we have constructed multiple ontologies that are inherently unique but are related to each other. The system performs ontology alignment to allow for inter-operation between them. Also, it provides a natural language query (NLQ) interface. It converts the Natural Language (NL) input to SPARQL query. It answers queries across these multiple ontologies and abstracts them as a single linked unit. Currently, it is working for simple as well as some type of complex queries. General Terms Semantic search, Ontology, Natural Language Processing (NLP)

Constructing an interactive natural language interface for relational databases

Natural language has been the holy grail of query interface designers, but has generally been considered too hard to work with, except in limited specific circumstances. In this paper, we describe the architecture of an interactive natural language query interface for relational databases. Through a carefully limited interaction with the user, we are able to correctly interpret complex natural language queries, in a generic manner across a range of domains. By these means, a logically complex English language sentence is correctly translated into a SQL query, which may include aggregation, nesting, and various types of joins, among other things, and can be evaluated against an RDBMS. We have constructed a system, NaLIR (Natural Language Interface for Relational databases), embodying these ideas. Our experimental assessment, through user studies, demonstrates that NaLIR is good enough to be usable in practice: even naive users are able to specify quite complex ad-hoc queries.

SemanticDB: A Semantic Web Infrastructure for Clinical Research and Quality Reporting

Semantic Web technologies offer the potential to revolutionize management of health care data by increasing interoperability and reusability while reducing the need for redundant data collection and storage. From 1998 through 2010, Cleveland Clinic sponsored a project designed to explore and develop this potential. The product of this effort, SemanticDB, is a suite of software tools and knowledge resources built to facilitate the collection, storage and use of the diverse data needed to conduct clinical research and health care quality reporting. SemanticDB consists of three main components: 1) a content repository driven by a meta-model that facilitates collection and integration of data in an XML format and automatically converts the data to RDF; 2) an inference-mediated, natural language query interface designed to identify patients who meet complex inclusion and exclusion criteria; and 3) a data production pipeline that uses inference to generate customized views of the repository content for statistical analysis and reporting. Since 2008, this system has been used by the Cleveland Clinic's Heart and Vascular Institute to support numerous clinical investigations, and in 2009 Cleveland Clinic was certified to submit data produced in this manner to national quality monitoring databases sponsored by the Society of Thoracic Surgeons and the American College of Cardiology.

NaLIX

We describe the construction of a generic natural language query interface to an XML database. Our interface can accept a large class of English sentences as a query, which can be quite complex and include aggregation, nesting, and value joins, among other things. This query is translated, potentially after reformulation, into an XQuery expression. The translation is based on mapping grammatical proximity of natural language parsed tokens in the parse tree of the query sentence to proximity of corresponding elements in the XML data to be retrieved. Iterative search in the form of followup queries is also supported. Our experimental assessment, through a user study, demonstrates that this type of natural language interface is good enough to be usable now, with no restrictions on the application domain.

An adaptive multilingual interface for tourism information

We have developed a natural language query interface for Tiscover, the largest Austrian web-based tourism platform. For a period of ten days, this interface was made publicly available by means of an advertisement and a hyperlink on Tiscover's homepage. In this paper, we will describe the results and our insights from analysing the natural language queries collected during this field trial. This analysis shows how users formulate queries when their imagination is not limited by conventional search interfaces with structured forms consisting of check boxes, radio buttons and special-purpose text fields. The results of this field trial are thus valuable indicators for determining direction, the web-based tourism information system should be extended into, in order to better serve the customers.

A natural language user interface for fuzzy scope queries.

This paper presents a two-agent framework to build a natural language query interface for IC information system, focusing more on scope queries in a single English sentence. The first agent, parsing agent, syntactically processes and semantically interprets natural language sentence to construct a fuzzy structured query language (SQL) statement. The second agent, defuzzifying agent, defuzzifies the imprecise part of the fuzzy SQL statement into its equivalent executable precise SQL statement based on fuzzy rules. The first agent can also actively ask the user some necessary questions when it manages to disambiguate the vague retrieval requirements. The adaptive defuzzification approach employed in the defuzzifying agent is discussed in detail. A prototype interface has been implemented to demonstrate the effectiveness.

Handling Grammatical Errors, Ambiguity and Impreciseness in GIS Natural Language Queries

A natural language query interface is very desirable for a geographic information system (GIS). It converts natural language queries (sentences) into a formal query language. A key task in building a natural language query interface is handling uncertainty and impreciseness. Grammatical errors and parsing ambiguity cause uncertainty. A natural language query may contain imprecise terms that have to be processed before an executable query can be generated. In this paper, a three–step technique is presented that can be used to correct grammatically incomplete natural language queries, solve parsing ambiguity, and translate imprecise conditions into executable selection conditions.

Word segmentation based on database semantics in NChiql

In this paper a novel word-segmentation algorithm is presented to delimit words in Chinese natural language queries in NChiql system, a Chinese natural language query interface to databases. Although there are sizable literatures on Chinese segmentation, they cannot satisfy particular requirements in this system. The novel word-segmentation algorithm is based on the database semantics, namely Semantic Conceptual Model (SCM) for specific domain knowledge. Based on SCM, the segmenter labels the database semantics to words directly, which eases the disambiguation and translation (from natural language to database query) in NChiql.

Aspects of the automatic generation of SQL statements in a natural language query interface

In Natural Language Interfaces to databases it is currently a widely accepted technique to use an intermediate semantic representation of the NL sentences which is more or less based on First Order Predicate Logic, eventually augmented by some specific functions inherent to the database query language like, e.g. the aggregation functions of SQL. However, in order not to restrict the full power of NL one also has to augment the SQL language in some way, because SQL has some restrictions and shortcomings, of which the lack of a loop capability for handling ordinals (e.g. the 3rd lowest …, the 5th highest …) is the most serious. In this paper such an augmentation (which we call SQL +) is presented, and it is shown that—observing some simple rules—a NL sentence can be mapped from its internal representation to SQL + in a straightforward and uniform manner. Though these SQL + expressions may not always be optimal from a performance point of view, they have some advantages which we consider to be more useful.