Developing a natural language interface to complex data
ACM Transactions on Database Systems (TODS)
What happened when database researchers met usability
Information Systems
An efficient easily adaptable system for interpreting natural language queries
Computational Linguistics
The energy data collection project
dg.o '00 Proceedings of the 2000 annual national conference on Digital government research
A portal for access to complex distributed information about energy
dg.o '02 Proceedings of the 2002 annual national conference on Digital government research
A question/answer typology with surface text patterns
HLT '02 Proceedings of the second international conference on Human Language Technology Research
A portal for access to complex distributed information about energy
dg.o '02 Proceedings of the 2002 annual national conference on Digital government research
Extending metadata definitions by automatically extracting and organizing glossary definitions
dg.o '03 Proceedings of the 2003 annual national conference on Digital government research
Extending metadata definitions by automatically extracting and organizing glossary definitions
dg.o '03 Proceedings of the 2003 annual national conference on Digital government research
Hi-index | 0.00 |
Even quite sophisticated users can experience difficulty navigating large collections of data to locate the answers to their queries. We describe AskCal, a system that employs natural language processing, an ontology, a query planner, and various feedback mechanisms to assist a user in refining his or her query and then in executing and visualizing it. We trace several interactions with AskCal in the domain of energy time series, and show how a combination of modalities, including ATN parsing of free-form natural language questions, user modification of predefined template queries, and fall-back parsing by picking out landmark terms, support a wide variety of user queries while reducing user query formulation effort. We illustrate the use of ontology- and data-based feedback mechanisms to guide the user toward regions of the query space where useful data can be found. We show how organizing and harmonizing the metadata into an overarching domain model supports user navigation as well as query planning.