tailieunhanh - Báo cáo khoa học: "EVALUATION OF NATURAL LANGUAGE INTERFACES TO DATABASE SYSTEMS: A PANEL DISCUSSION "

For a natural language access to database system to be practical it must achieve a good match between the capabilities of the user and the requirements of the task. The user brings his own natural language and his own style of interaction to the system. The task brings the questions that must be answered and the database domaln+s semantics. All natural language access systems achieve some degree of success. But to make progress as a field, we need to be able to evaluate the degree of this success. For too long, the best we have menaged has been to. | EVALUATION OF NATURAL LANGUAGE INTERFACES TO DATABASE SYSTEMS A PANEL DISCUSSION Norman K. Sondheimer Chair Sperry Univac Blue Bell PA For a natural language access to database system to be practical it must achieve a good match between the capabilities of the user and the requirements of the task. The user brings his own natural language and his own style of interaction to the system. The task brings the questions that must be answered and the database domain s semantics. All natural language access systems achieve some degree of success. But to make progress as a field we need to be able to evaluate the degree of this success. For too long the best we have managed has been to produce a list of typical questions or linguistic phenomena that a system correctly processed. Missing has been a discussion of their importance and a similar list of unhandled phenomena. Only occasionally were even informal evaluations of systems conducted. Recently this has begun to change. In the last several years many of the current generation of natural language access to database systems have been subject to laboratory or field testing. These include INTELLECT LADDER PLANES REL and TQA. we have begun to discover what a user will ask a system how he reacts to its limits and where we need further work. This panel brings together a good sampling of the people involved in these tests Including individuals intimately involved with the above systems. The position papers that follow present their unique viewpoints on the important issues in the evaluation of natural language access to database systems. These Include I. What has been learned about a user needs b system s capabilities and c their match with respect to tasks. Under this what are the most Important linguistic phenomena to allow for What other kinds of Interactions beside retrievals do users request How good are systems at satisfying users How good are users at finding ways to use systems How satisfied are users with systems .

• Báo cáo khoa học
• EVALUATION OF NATURAL LANGUAGE
• INTERFACES TO DATABASE SYSTEMS
• A PANEL DISCUSSION
• scientific reports
• model language
• process natural language
• INTERFACES TO DATA BASE SYSTEMS
• Bozena Henisz
• Towards Web Based
• Evaluation of Automatic Natural Language
• Phrase Generation
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• SELECTIVE PLANNING
• INTERFACE EVALUATION
• William C
• Mann
• What Makes Evaluation Hard
• Long Papers
• Workshops
• Theoretical Evaluation
• Estimation Methods
• Data Oriented Parsing
• Human Evaluation
• German Surface Realisation Ranker
• Toward Evaluation of Writing Style Finding Overly
• Repetitive Word Use
• Student Essays
• Applications of Automatic Evaluation Methods
• Measuring a Capability
• Speech Translation System
• End to End Evaluation
• Simultaneous Translation
• Olivier Hamon
• Text Summarization Evaluation
• Lynette Hirschman
• Contents and evaluation
• Slovenian German online dictionary
• Birte Liinneker
• Cross Framework Evaluation
• Statistical Parsing
• Reut Tsarfaty
• Word Sense Induction
• Triplet Based Clustering
• Automatic Evaluation
• A Figure of Merit
• the Evaluation of Web Corpus Randomness
• Massimiliano Ciaramita Marco Baroni
• Efficient MT Evaluation
• Block Movements
• Gregor Leusch and Nicola Ueffing and Hermann Ney
• Comparing Automatic
• NLG Systems