tailieunhanh - Báo cáo khoa học: "BUILDING NON-NORMATIVE SYSTEMS - THE SEARCH FOR ROBUSTNESS AN OVERVIEW"

Many natural language understanding systems behave much like the proverbial high school english teacher who simply fails to understand any utterance which doesn't conform to that teacher's inviolable standard of english usage. But while the teacher merely pretends not to understand, our systems really don't. The teacher consciously stonewalls when confronted with non-standard usage to prescribe quite rigidly what is acceptable linguistic usage and what is not. | BUILDING NON-NORMATIVE SYSTEMS - THE SEARCH FOR ROBUSTNESS AN OVERVIEW Mitchell p. Marcus Bell Laboratories Murray Hill New Jersey 07974 Many natural language understanding systems behave much like the proverbial high school engllsh teacher who simply falls to understand any utterance which doesn t conform to that teacher s Inviolable standard of engllsh usage. But while the teacher merely pretends not to understand our systems really don t. The teacher consciously stonewalls when confronted with non-standard usage to prescribe quite rigidly what Is acceptable linguistic usage and what Is not. What Is so artificial about this behaviour of course Is that our Implicit linguistic models are descriptive and not prescriptive they model what we expect not what we demand. People are quite good at understanding language which they when asked would consider to be non-standard in some way or other. Our programs on the other hand tend to be very rigid. They usually fall to degrade gracefully when their Internal models of syntax semantics or pragmatics are violated by user Input. In essence the models of linguistic well-formedness which these programs embody become normative they prescribe quite rigidly what Is considered standard linguistic usage and what isn t. Old solutions to this problem Include extending a system s linguistic coverage or Intentionally excluding linguistic constraints that are occasionally violated by speakers. But neither of these approaches changes the fundamental situation - that when confronted with Input which falls to conform to the system builder s expectations however broad and however loose the system will entirely reject the input. Furthermore these techniques bar a system from utilizing the fact that people normally do obey certain linguistic standards even If they violate them on occasion. More recently a range of approaches have been investigated that allow a system to behave more robustly when confronted with Input which violates its .

• Báo cáo khoa học
• BUILDING NON NORMATIVE SYSTEMS
• THE SEARCH FOR ROBUSTNESS AN OVERVIEW
• Mitchell P
• Marcus Bell
• scientific reports
• model language
• process natural language
• Dialog Control
• Natural Language System
• Dialog Control in a Natural Language System
• Expanding the Horizons
• Natural Language Interfaces
• Phil Hayes
• PROSPECTS OR PRACTICAL
• NATURAL LANGUAGE SYSTEMS
• Workshops
• NATURAL LANGUAGE
• INTERACTION WITH MACHINES
• Long Papers
• COMPUTER INTEBFACE DESIGN MURRAY TUROFF DEPARTMENT OF COMPUTER
• IiVFORMATION SCIENCE IIEW JERSEY INSTITUTE OF TECHNOLOGY
• EVALUATION OF NATURAL LANGUAGE
• INTERFACES TO DATABASE SYSTEMS
• A PANEL DISCUSSION
• database query system
• J
• Norwood Crout
• INTERFACES TO DATA BASE SYSTEMS
• Bozena Henisz
• INTERPRETING NATURAL LANGUAGE
• DATABASE UPDATES
• S
• Jermld Kaplan Jim David
• TRANSPORTABLE NATURAL LANGUAGE
• INTERFACES TO DATABASES
• Gary G
• Hendrlx and William H
• Lewis
• DATABASES THEORETICAL
• TECHNICAL ISSUES
• TRANSPORTABLE NATURAL LANGUAGE INTERFACES
• PROBLEMS AND TECHNIQUES
• Barbara J
• Grosz
• THEORETICAL TECHNICAL ISSUES
• NATURAL LANGUAGE ACCESS TO DATABASES
• R
• Petrick
• Domain Independent
• Database Access Systems
• ISSUES IN NATURAL LANGUAGE
• ACCESS TO DATABASES
• A LOGIC PROGRAMMING PERSPECTIVE
• Sharon C
• Salveter David Maier
• PLANNING NATURAL LANGUAGE
• EXPRESSIONS REFERRING
• Douglas E
• Appelt
• THE TEXT SYSTEM
• NATURAL LANGUAGE GENERATION
• Kathleen R
• M
• MENTING A DATABASE
• KNOWLEDGE REPRESENTATION
• THE KEY TO THE SELECTION PROBLEM
• E
• Jeffrey Conklin David D
• McDonald
• A KNOWLEDGE ENGINEERING
• NATURAL LANGUAGE UNDERSTANDING
• Stuart C
• Shapiro
• NATURAL LANGUAGE TEXTS
• NECESSARILY GRAMMATICAL
• EVEN COMPLETE
• UNGRAMHATICALITY
• EXTRA GRAMMATICALITY
• NATURAL LANGUAGE UNDERSTANDING SYSTEMS
• Taxonomy
• Descriptions
• Individuals in Natural
• Language Understanding
• The Use of Ooject Special Knowledge
• Natural Language Processing
• Mark H
• Bursteln