Term Disambiguation in Natural Language Query for XML

Converting a natural language query sentence into a formal database query is a major challenge. We have constructed NaLIX, a natural language interface for querying XML data. Through our experience with NaLIX, we find that failures in natural language query understanding can often be dealt with as ambiguities in term meanings. These failures are typically the result of either the user's poor knowledge of the database schema or the system's lack of linguistic coverage. With automatic term expansion techniques and appropriate interactive feedback, we are able to resolve these ambiguities. In this paper, we describe our approach and present results demonstrating its effectiveness.

[1]  James D. Hollan,et al.  Edit wear and read wear , 1992, CHI.

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

[3]  Louis M. Gomez,et al.  SuperBook: an automatic tool for information exploration—hypertext? , 1987, Hypertext.

[4]  Jerry Alan Fails,et al.  A design tool for camera-based interaction , 2003, CHI '03.

[5]  Dekang Lin,et al.  Dependency-Based Evaluation of Minipar , 2003 .

[6]  Jan Svartvik,et al.  A __ comprehensive grammar of the English language , 1988 .

[7]  Soumen Chakrabarti,et al.  Keyword Search in Databases , 2007 .

[8]  H. V. Jagadish,et al.  NaLIX: an interactive natural language interface for querying XML , 2005, SIGMOD '05.

[9]  Yoichi Shinoda,et al.  Information filtering based on user behavior analysis and best match text retrieval , 1994, SIGIR '94.

[10]  Divesh Srivastava,et al.  Keyword proximity search in XML trees , 2006 .

[11]  Sebastian van Delden,et al.  Retrieving NASA problem reports: a case study in natural language information retrieval , 2004, Data Knowl. Eng..

[12]  Laura A. Dabbish,et al.  Labeling images with a computer game , 2004, AAAI Spring Symposium: Knowledge Collection from Volunteer Contributors.

[13]  H. V. Jagadish,et al.  Constructing a Generic Natural Language Interface for an XML Database , 2006, EDBT.

[14]  Agathoniki Trigoni,et al.  Interactive Query Formulation in Semistructured Databases , 2002, FQAS.

[15]  Vagelis Hristidis,et al.  Keyword proximity search on XML graphs , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).

[16]  Roberto Navigli,et al.  An analysis of ontology-based query expansion strategies , 2003 .

[17]  Yehoshua Sagiv,et al.  XSEarch: A Semantic Search Engine for XML , 2003, VLDB.

[18]  Jennifer Chu-Carroll,et al.  A Hybrid Approach to Natural Language Web Search , 2002, EMNLP.

[19]  Dietmar F. Rösner,et al.  NAUDA: a cooperative natural language interface to relational databases , 1993, SIGMOD '93.

[20]  Antonio Torralba,et al.  LabelMe: A Database and Web-Based Tool for Image Annotation , 2008, International Journal of Computer Vision.

[21]  Sandeep Purao,et al.  A Heuristic-Based Methodology for Semantic Augmentation of User Queries on the Web , 2003, ER.

[22]  Epaminondas Kapetanios,et al.  Query Construction through Meaningful Suggestions of Terms , 2002, FQAS.

[23]  Feng Shao,et al.  XRANK: ranked keyword search over XML documents , 2003, SIGMOD '03.

[24]  David Stallard,et al.  A Terminological Simplification Transformation for Natural Language Question-Answering Systems , 1986, HLT.

[25]  Cong Yu,et al.  Schema-Free XQuery , 2004, VLDB.

[26]  W. Bruce Croft,et al.  Query expansion using local and global document analysis , 1996, SIGIR '96.

[27]  Marcia J. Bates,et al.  The design of browsing and berrypicking techniques for the online search interface , 1989 .