A natural language interface plug-in for cooperative query answering in biological databases

Abstract

BackgroundOne of the many unique features of biological databases is that the mere existence of a ground data item is not always a precondition for a query response. It may be argued that from a biologist's standpoint, queries are not always best posed using a structured language. By this we mean that approximate and flexible responses to natural language like queries are well suited for this domain. This is partly due to biologists' tendency to seek simpler interfaces and partly due to the fact that questions in biology involve high level concepts that are open to interpretations computed using sophisticated tools. In such highly interpretive environments, rigidly structured databases do not always perform well. In this paper, our goal is to propose a semantic correspondence plug-in to aid natural language query processing over arbitrary biological database schema with an aim to providing cooperative responses to queries tailored to users' interpretations.ResultsNatural language interfaces for databases are generally effective when they are tuned to the underlying database schema and its semantics. Therefore, changes in database schema become impossible to support, or a substantial reorganization cost must be absorbed to reflect any change. We leverage developments in natural language parsing, rule languages and ontologies, and data integration technologies to assemble a prototype query processor that is able to transform a natural language query into a semantically equivalent structured query over the database. We allow knowledge rules and their frequent modifications as part of the underlying database schema. The approach we adopt in our plug-in overcomes some of the serious limitations of many contemporary natural language interfaces, including support for schema modifications and independence from underlying database schema.ConclusionsThe plug-in introduced in this paper is generic and facilitates connecting user selected natural language interfaces to arbitrary databases using a semantic description of the intended application. We demonstrate the feasibility of our approach with a practical example.

Knowledge Rich Natural Language Queries over Structured Biological Databases

“…The novelty of our system is that such knowledge is derived by the system on its own and no explicit requests need to be made. In a more recent work [32,31], it was shown that an ontology based logical query language ConLog can be used to non-intrusively capture semantic knowledge and query response generated without such explicit knowledge entailed response computation. In this paper, our goal is to show that a canonical representation, as shown in figures 3(a) through 3(f), can be used to compose queries in a logic based language such as Datalog without user intervention.…”

“…Augmenting structured databases with semantic knowledge for the purpose of knowledge rich queries have been studied in the context of NLQs [32,31], and structured database integration [34]. Despite many such efforts, articulating application description by domain scientists in Biology to facilitate knowledge rich queries remain a significant challenge.…”

“…In Schema-Free SQL [48], meta information such as relation trees were used to aid query processors to tolerate mismatch or errors in schema information, and in BioVis [34] and ConLog [31] conceptual structures were leveraged to map queries properly to underlying scheme. In BioSmart the need for such a structure to appropriately select parts of schema to frame the queries is much greater.…”

An authoring tool for decision support systems in context questions of ecological knowledge

“…Cimiano et al (2009) describes different paradigms proposed in the past for querying information collections, among them form filling, query-by-example or menu-based approaches, as well as NLIs, either relying on controlled language or on more or less free language input. Obviously, Natural Language (NL) searching probably constitute the most flexible and effective approach for interrogating a biological DB (Jamil, 2012). Since many biological DBs (e.g.…”

“…GenBank or UCSC Genome Browser) employ graphical interfaces that are not prepared for arbitrary questioning, previous effort has been made to build NL strategies oriented to Biomedicine and Biotechnology DBs (e.g. Jamil, 2012;Goldsmith et al, 2009;Clegg & Shepherd, 2007;Distelhorst et al, 2003). As Cimiano et al (2009) states, while the querying paradigm based on NL is generally deemed to be the most intuitive from a usage point of view, it has also been shown to be the most difficult to realize effectively.…”