Synthesizing structured text from logical database subsets

ABSTRACT

In the classical database world, information access has been based on a paradigm that involves structured, schema-aware, queries and tabular answers. In the current environment, however, where information prevails in most activities of society, serving people, applications, and devices in dramatically increasing numbers, this paradigm has proved to be very limited. On the query side, much work has been done on moving towards keyword queries over structured data. In our previous work, we have touched the other side as well, and have proposed a paradigm that generates entire databases in response to keyword queries. In this paper, we continue in the same direction and propose synthesizing textual answers in response to queries of any kind over structured data. In particular, we study the transformation of a dynamically-generated logical database subset into a narrative through a customizable, extensible, and templatebased process. In doing so, we exploit the structured nature of database schemas and describe three generic translation modules for different formations in the schema, called unary, split, and join modules. We have implemented the proposed translation procedure into our own database front end and have performed several experiments evaluating the textual answers generated as several features and parameters of the system are varied. We have also conducted a set of experiments measuring the effectiveness of such answers on users. The overall results are very encouraging and indicate the promise that our approach has for several applications.

REFERENCES

• 1: www.diligentproject.org.
• 2: DBXplorer: A System for Keyword-Based Search over Relational Databases, Proceedings of the 18th International Conference on Data Engineering, p.5, February 26-March 01, 2002
• 3: I. Androutsopoulos, G. D. Ritchie, and P. Thanisch. Natural language interfaces to databases - an introduction. CoRR, cmp-lg/9503016, 1995.
• 4: AT&T Labs Inc. - Research. Text-to-speech (TTS), The synthesis of audible speech from text. url: http://www.research.att.com/ttsweb/tts/index.php#top, March 2007.
• 5: Bell Labs. Text-to-speech synthesis. url: http://www.bell-labs.com/project/tts, March 2007.
• 6: Ron Cole, Survey of the state of the art in human language technology, Cambridge University Press, New York, NY, 1997
• 7: P. Dixon. Basics of Oracle text retrieval. IEEE Data Eng. Bull., 24(4):11--14, 2001.
• 8: Daniela Florescu , Donald Kossmann , Ioana Manolescu, Integrating keyword search into XML query processing, Computer Networks: The International Journal of Computer and Telecommunications Networking, v.33 n.1-6, p.119-135, June 2000
• 9: Jens Graupmann , Ralf Schenkel , Gerhard Weikum, The SphereSearch engine for unified ranked retrieval of heterogeneous XML and web documents, Proceedings of the 31st international conference on Very large data bases, August 30-September 02, 2005, Trondheim, Norway
• 10: Lin Guo , Feng Shao , Chavdar Botev , Jayavel Shanmugasundaram, XRANK: ranked keyword search over XML documents, Proceedings of the 2003 ACM SIGMOD international conference on Management of data, June 09-12, 2003, San Diego, California [doi>10.1145/872757.872762]
• 11: J. R. Hamilton and T. K. Nayak. Microsoft SQL server full-text search. IEEE Data Eng. Bull., 24(4):7--10, 2001.
• 12: Vagelis Hristidis , Luis Gravano , Yannis Papakonstantinou, Efficient IR-style keyword search over relational databases, Proceedings of the 29th international conference on Very large data bases, p.850-861, September 09-12, 2003, Berlin, Germany
• 13: V. Hristidis, Y. Papakonstantinou, and A. Balmin. Keyword proximity search on XML graphs. In ICDE, pages 367--378, 2003.
• 14: Varun Kacholia , Shashank Pandit , Soumen Chakrabarti , S. Sudarshan , Rushi Desai , Hrishikesh Karambelkar, Bidirectional expansion for keyword search on graph databases, Proceedings of the 31st international conference on Very large data bases, August 30-September 02, 2005, Trondheim, Norway
• 15: Georgia Koutrika , Alkis Simitsis , Yannis Ioannidis, Précis: The Essence of a Query Answer, Proceedings of the 22nd International Conference on Data Engineering, p.69, April 03-07, 2006 [doi>10.1109/ICDE.2006.114]
• 16: A. Maier and D. E. Simmen. DB2 optimization in support of full text search. IEEE Data Eng. Bull., 24(4):3--6, 2001.
• 17: Elisabeth Métais, Enhancing information systems management with natural language processing techniques, Data & Knowledge Engineering, v.41 n.2-3, p.247-272, June 2002 [doi>10.1016/S0169-023X(02)00043-5]
• 18: Elisabeth Métais , Jean-Noël Meunier , Gilles Levreau, Database Schema Design: A Perspective From Natural Language Techniques to Validation and View Integration, Proceedings of the 12th International Conference on the Entity-Relationship Approach: Entity-Relationship Approach, p.190-205, December 15-17, 1993
• 19: M. Minock. A phrasal approach to natural language interfaces over databases. In NLDB, pages 333--336, 2005.
• 20: Tanja Schultz , Katrin Kirchhoff, Multilingual Speech Processing, Academic Press, Inc., Orlando, FL, 2006
• 21: A. Simitsis and G. Koutrika. Comprehensible answers to précis queries. In CAiSE, pages 142--156, 2006.
• 22: Alkis Simitsis , Georgia Koutrika , Yannis Ioannidis, Précis: from unstructured keywords as queries to structured databases as answers, The VLDB Journal — The International Journal on Very Large Data Bases, v.17 n.1, p.117-149, January 2008 [doi>10.1007/s00778-007-0075-9]
• 23: Eriks Sneiders, Automated Question Answering Using Question Templates That Cover the Conceptual Model of the Database, Proceedings of the 6th International Conference on Applications of Natural Language to Information Systems-Revised Papers, p.235-239, June 27-28, 2002
• 24: Veda C. Storey, Understanding and Representing Relationship Semantics in Database Design, Proceedings of the 5th International Conference on Applications of Natural Language to Information Systems-Revised Papers, p.79-90, June 28-30, 2000
• 25: V. C. Storey , R. C. Goldstein , H. Ullrich, Naive Semantics to Support Automated Database Design, IEEE Transactions on Knowledge and Data Engineering, v.14 n.1, p.1-12, January 2002 [doi>10.1109/69.979969]
• 26: A. Toral, E. Noguera, F. Llopis, and R. Muñoz. Improving question answering using named entity recognition. In NLDB, pages 181--191, 2005.
• 27: Q. Wang, C. Nass, and J. Hu. Natural language query vs. keyword search: Effects of task complexity on search performance, participant perceptions, and preferences. In INTERACT, pages 106--116, 2005.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.1 Logical Design
          Subjects: Schema and subschema