Question Answering Techniques Research Articles

Object-Relational Database Based Category Data Model for Natural Language Interface to Database

Domain specific question answering technique allows users to use natural language to express their queries so that users need not have the knowledge about the structures of the information source. For such an application relational model is not suitable as it is not a natural way to represent real world knowledge. Using relational model for representing information source results in scattered relations of data about the real world objects. In this paper an effective category model is presented to organize information according to their contents based on object-relational database. For the discussion of the category model railway domain is used in the paper.

FIDJI: using syntax for validating answers in multiple documents

This article presents FIDJI, a question-answering (QA) system for French. FIDJI combines syntactic information with traditional QA techniques such as named entity recognition and term weighting; it does not require any pre-processing other than classical search engine indexing. Among other uses of syntax, we experiment in this system the validation of answers through different documents, as well as specific techniques for answering different types of questions (e.g., yes/no or list questions). We present several experiments which show the benefits of syntactic analysis, as well as multi-document validation. Different types of questions and corpora are tested, and specificities are commented. Links with result aggregation are also discussed.

Biomedical question answering: A survey

Objectives In this survey, we reviewed the current state of the art in biomedical QA (Question Answering), within a broader framework of semantic knowledge-based QA approaches, and projected directions for the future research development in this critical area of intersection between Artificial Intelligence, Information Retrieval, and Biomedical Informatics. Materials and methods We devised a conceptual framework within which to categorize current QA approaches. In particular, we used “semantic knowledge-based QA” as a category under which to subsume QA techniques and approaches, both corpus-based and knowledge base (KB)-based, that utilize semantic knowledge-informed techniques in the QA process, and we further classified those approaches into three subcategories: (1) semantics-based, (2) inference-based, and (3) logic-based. Based on the framework, we first conducted a survey of open-domain or non-biomedical-domain QA approaches that belong to each of the three subcategories. We then conducted an in-depth review of biomedical QA, by first noting the characteristics of, and resources available for, biomedical QA and then reviewing medical QA approaches and biological QA approaches, in turn. The research articles reviewed in this paper were found and selected through online searches. Results Our review suggested the following tasks ahead for the future research development in this area: (1) Construction of domain-specific typology and taxonomy of questions (biological QA), (2) Development of more sophisticated techniques for natural language (NL) question analysis and classification, (3) Development of effective methods for answer generation from potentially conflicting evidences, (4) More extensive and integrated utilization of semantic knowledge throughout the QA process, and (5) Incorporation of logic and reasoning mechanisms for answer inference. Conclusion Corresponding to the growth of biomedical information, there is a growing need for QA systems that can help users better utilize the ever-accumulating information. Continued research toward development of more sophisticated techniques for processing NL text, for utilizing semantic knowledge, and for incorporating logic and reasoning mechanisms, will lead to more useful QA systems.

Open-domain textual question answering techniques

Textual question answering is a technique of extracting a sentence or text snippet from a document or document collection that responds directly to a query. Open-domain textual question answering presupposes that questions are natural and unrestricted with respect to topic. The question answering (Q/A) techniques, as embodied in today's systems, can be roughly divided into two types: (1) techniques for Information Seeking (IS), which localize the answer in vast document collections; and (2) techniques for Reading Comprehension (RC) that answer a series of questions related to a given document. Although these two types of techniques and systems are different, it is desirable to combine them for enabling more advanced forms of Q/A. This paper discusses an approach that successfully enhanced an existing IS system with RC capabilities. This enhancement is important because advanced Q/A, as exemplified by the ARDA AQUAINT program, is moving towards Q/A systems that incorporate semantic and pragmatic knowledge enabling dialogue-based Q/A. Because today's RC systems involve a short series of questions in context, they represent a rudimentary form of interactive Q/A which constitutes a possible foundation for more advanced forms of dialogue-based Q/A.

Scaling question answering to the web

The wealth of information on the web makes it an attractive resource for seeking quick answers to simple, factual questions such as “who was the first American in space?” or “what is the second tallest mountain in the world?” Yet today's most advanced web search services (e.g., Google and AskJeeves) make it surprisingly tedious to locate answers to such questions. In this paper, we extend question-answering techniques, first studied in the information retrieval literature, to the web and experimentally evaluate their performance.First we introduce Mulder, which we believe to be the first general-purpose, fully-automated question-answering system available on the web. Second, we describe Mulder's architecture, which relies on multiple search-engine queries, natural-language parsing, and a novel voting procedure to yield reliable answers coupled with high recall. Finally, we compare Mulder's performance to that of Google and AskJeeves on questions drawn from the TREC-8 question answering track. We find that Mulder's recall is more than a factor of three higher than that of AskJeeves. In addition, we find that Google requires 6.6 times as much user effort to achieve the same level of recall as Mulder.