TAILIEUCHUNG - Báo cáo khoa học: "ON THE LINGUISTIC CHARACTER OF NON-STANDARD INPUT"

If natural language understanding systems are ever to cope with the full range of English language forms, their designers will have to incorporate a number of features of the spoken vernacular language. This communication discusses such features as non-standard grammatical rules, hesitations and false starts due to self-correction, systematic errors due to mismatches between the grammar and sentence generator, and uncorrected true errors. | ON THE LINGUISTIC CHARACTER OF NON-STANDARD INPUT Anthony s. Kroch and Donald Hindle Department of Linguistics University of Pennsylvania Philadelphia PA 19104 USA ABSTRACT If natural language understanding systems are ever to cope with the full range of English language forms their designers will have to Incorporate a number of features of the spoken vernacular language. This communication discusses such features as non-standard grammatical rules hesitations and false starts due to self-correction systematic errors due to mismatches between the grammar and sentence generator and uncorrected true errors. There are many ways In which the Input to a natural language system can be non-standard without being unlnterpretable . Most obviously such input can be the well-formed output of a grammar other than the standard language grammar with which the interpreter is likely to be equipped. This difference of grammar is presumably what we notice in language that we call non-standard in everyday life. Obviously at least from the perspective of a linguist it Is wrong to think of this difference as being due to errors made by the non-standard language user It is simply a dialect difference. Secondly the non-standard Input can contain hesitations and self-corrections which make the string unlnterpretable unless some parts of It are edited out. This is the normal state of affairs In spoken language so that any system designed to understand spoken communication even at a rudimentary level must be able to edit Its Input as well as Interpret it. Thirdly the input may be ungrammatical even by the rules of the grammar of the speaker but be the expected output of the speaker s sentence generating device. This case has not been much discussed but it is Important because In certain environments speakers and to some extent unskilled writers regularly produce ungrammmatlcal output in preference to grammatically unimpeachable alternatives. Finally the input that the system receives may .

• Báo cáo khoa học
• ON THE LINGUISTIC CHARACTER
• NON STANDARD INPUT
• Anthony S
• Kroch and Donald Hindle
• scientific reports
• model language
• process natural language
• Stock market
• Turning point
• Linguistic codex
• Non Random character
• CCMNP panel variable
• 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