Composing Questions through Conceptual Authoring

This article describes a method for composing fluent and complex natural language questions, while avoiding the standard pitfalls of free text queries. The method, based on Conceptual Authoring, is targeted at question-answering systems where reliability and transparency are critical, and where users cannot be expected to undergo extensive training in question composition. This scenario is found in most corporate domains, especially in applications that are risk-averse. We present a proof-of-concept system we have developed: a question-answering interface to a large repository of medical histories in the area of cancer. We show that the method allows users to successfully and reliably compose complex queries with minimal training.

[1]  Harry R. Tennant,et al.  Usable natural language interfaces through menu-based natural language understanding , 1983, CHI '83.

[2]  Richard Power,et al.  Generation as a Solution to Its Own Problem , 1998, INLG.

[3]  Peter Thanisch,et al.  MASQUE/SQL: an efficient and portable natural language query interface for relational databases , 1993 .

[4]  Cynthia Brandt,et al.  Application of Information Technology: Metadata-driven Ad Hoc Query of Patient Data: Meeting the Needs of Clinical Studies , 2002, J. Am. Medical Informatics Assoc..

[5]  Prakash M. Nadkarni,et al.  Data Extraction and Ad Hoc Query of an Entity– Attribute–Value Database , 2000 .

[6]  Eva-Martin Mueckstein.  Controlled natural language interfaces (extended abstract): the best of three worlds , 1985, CSC '85.

[7]  Carole D. Hafner,et al.  Portability of syntax and semantics in DATALOG , 1985, TOIS.

[8]  Richard McClatchey,et al.  Resolving Clinicians’ Queries Across a Grid’s Infrastructure , 2004, Methods of Information in Medicine.

[9]  Gary G. Hendrix,et al.  Developing a natural language interface to complex data , 1977, TODS.

[10]  Catalina Hallett.  Generic Querying of Relational Databases using Natural Language Generation Techniques , 2006, INLG.

[11]  Donia Scott,et al.  PILLS: Multilingual generation of medical information documents with overlapping content , 2002, LREC.

[12]  Ioannis Androutsopoulos,et al.  Interfacing a Natural Language Front-End to a Relational Database , 1992 .

[13]  S. Jerrold Kaplan,et al.  Designing a Portable Natural Language Database Query System , 1984, TODS.

[14]  Nunzia Bettinsoli Giuse,et al.  Evidence-based databases versus primary medical literature: an in-house investigation on their optimal use. , 2004, Journal of the Medical Library Association : JMLA.

[15]  Gordon Davis,et al.  Effects of conceptual data modeling formalisms on user validation and analyst modeling of information requirements , 1990 .

[16]  Raymond J. Mooney,et al.  Using Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing , 2001, ECML.

[17]  Richard Power,et al.  What You See Is What You Meant: direct knowledge editing with natural language feedback , 1998, ECAI.

[18]  Tiziana Catarci,et al.  Are Visual Query Languages Easier to Use than Traditional Ones? An Experimental Proof , 1996, BCS HCI.

[19]  H. Uszkoreit,et al.  Querying Structured Knowledge Sources , 2005 .

[20]  Richard Power,et al.  Evaluation of the CLEF query interface , 2006 .

[21]  John D. Burger,et al.  Problems in Natural-Language Interface to DBMS With Examples From EUFID , 1983, ANLP.

[22]  Dipak Kalra,et al.  Design and Implementation of a Federated Health Record Server , 2001 .

[23]  George Hripcsak,et al.  Creating an environment for linking knowledge-based systems to a clinical database: a suite of tools , 1997, AMIA.

[24]  Richard Power,et al.  Multilingual Authoring Using Feedback Texts , 1998, COLING-ACL.

[25]  Lawrence A. Rowe,et al.  An exploratory study of ad hoc query languages to databases , 1992, [1992] Eighth International Conference on Data Engineering.

[26]  Paul Piwek,et al.  ITRI-00-12 Natural Language Generation in the MILE System , 2000 .

[27]  P. Gorman,et al.  A taxonomy of generic clinical questions: classification study , 2000, BMJ : British Medical Journal.

[28]  Yuval Shahar,et al.  Intelligent visualization and exploration of time-oriented clinical data , 1999, Proceedings of the 32nd Annual Hawaii International Conference on Systems Sciences. 1999. HICSS-32. Abstracts and CD-ROM of Full Papers.

[29]  Raymond Turner,et al.  A Formal Approach to Translating English into SQL , 1991, BNCOD.

[30]  K W Gish,et al.  Information needs of clinical teams: analysis of questions received by the Clinical Informatics Consult Service. , 2001, Bulletin of the Medical Library Association.

[31]  Oren Etzioni,et al.  Towards a theory of natural language interfaces to databases , 2003, IUI '03.

[32]  Eduard Hovy,et al.  A question/answer typology with surface text patterns , 2002 .

[33]  Rohit J. Kate,et al.  Learning to Transform Natural to Formal Languages , 2005, AAAI.

[34]  Bulletin of the medical library association april 1985. , 1985, Bulletin of the Medical Library Association.

[35]  James F. Allen.  Towards a General Theory of Action and Time , 1984, Artif. Intell..

[36]  Cynthia Brandt,et al.  Temporal query of attribute-value patient data: utilizing the constraints of clinical studies , 2003, Int. J. Medical Informatics.

[37]  Eric Brill,et al.  Automatic Question Answering: Beyond the Factoid , 2004, NAACL.

[38]  Peter Thanisch,et al.  Natural language interfaces to databases – an introduction , 1995, Natural Language Engineering.

[39]  Paul Piwek,et al.  Natural language processing in CLIME, a multilingual legal advisory system† , 2008, Natural Language Engineering.

[40]  Robert G. Crawford,et al.  Using a Natural Language Interface with Casual Users , 1990, Int. J. Man Mach. Stud..

[41]  Alan L. Rector,et al.  CLEF - Joining up Healthcare with Clinical and Post-Genomic Research , 2003 .

[42]  Paul Piwek,et al.  Requirements Definition, Validation, Verification and Evalation of the CLIME Interface and Language Processing Technology , 2006 .

[43]  Frank Meng,et al.  Query formulation from high-level concepts for relational databases , 1999, Proceedings User Interfaces to Data Intensive Systems.

[44]  Marian Petre,et al.  Why looking isn't always seeing: readership skills and graphical programming , 1995, CACM.