TAILIEUCHUNG - Báo cáo khoa học: "THE TEXT SYSTEM FOR NATURAL LANGUAGE GENERATION"

Computer-based generation of natural language requires consideration of two different types of problems: i) determining the content and textual shape of what is to be said, and 2) transforming that message into English. A computational solution to the problems of deciding what to say and how to organize it effectively is proposed that relies on an interaction between structural and semantic processes. Schemas, which encode aspects of discourse structure, are used to guide the generation process. A focusing mechanism monitors the use of t h e schemas, providing constraints on what can be said at any point. . | TOE TEXT SYSTEM FOR NATURAL LANGUAGE GENERATION AN OVERVIEW Kathleen R. McKeown Dept of Computer Information Science The Moore School University of Pennsylvania Philadelphia Pa. 19104 ABSTRACT Computer-based generation of natural language requires consideration of two different types of problems 1 determining the content and textual shape of what is to be said and 2 transforming that message into English. A computational solution to the problems of deciding what to say and how to organize it effectively is proposed that relies on an interaction between structural and semantic processes. Schemas which encode aspects of discourse structure are used to guide the generation process. A focusing mechanism monitors the use of the schemas providing constraints on what can be said at any point. These mechanisms have been implemented as part of a generation method within the context of a natural language database system addressing the specific problem of responding to questions about database structure. INTRODUCTION Deciding what to say and how to organize it effectively are two issues of particular importance to the generation of natural language text. In the past researchers have concentrated on local issues concerning the syntactic and lexical choices involved in transforming a pre-determined message into natural language. The research described here emphasizes a computational solution to the more global problems of determining the content and textual shape of what is to be said. More specifically my goals have been the development and application of principles of discourse structure discourse coherency and relevancy criterion to the computer generation of text. These principles have been realized in the TEXT system reported on in this paper. The main features of the generation method used in TEXT include 1 an ability to select relevant information 2 a system for pairing rhetorical techniques such as analogy with discourse purposes such as defining terms and 3 a .

• Báo cáo khoa học
• THE TEXT SYSTEM
• NATURAL LANGUAGE GENERATION
• Kathleen R
• M
• scientific reports
• model language
• process natural language
• The corpus based Vietnamese text to speech system
• The corpus based Vietnamese text
• Text tos peech
• ITU T P
• 85 standard
• Voice of Southern Vietnam
• Color atlas and text of histology
• Endocrine system
• Digestive system
• Female reproductive system
• Male reproductive system
• Urinary system
• Histology text and atlas
• Lymphatic system
• Integumentary system
• Associated structures
• Gastrointestinal tract
• An efficient hardware architecture
• HMM based TTS system
• Text to speech synthesis
• Text to speech synthesis system
• HTS to accelerate
• Nervous tissue
• Muscle tissue
• Respiratory system
• It Makes Sense
• A Wide Coverage Word Sense Disambiguation System
• Free Text
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Automatic Editing
• Back End Speech to Text System
• Maximilian Bisani Paul Vozila Olivier Divay Nuance
• xử lý ngôn ngữ tự nhiên
• Phoneme to Text
• Transcription System
• Infinite Vocabulary
• mô hình ngôn ngữ
• An Unsupervised System
• Identifying English Inclusions
• German Text
• High Throughput Modularized
• NLP System
• Clinical Text
• A Prototype Text to British
• Sign Language
• Translation System
• Dialog Navigator
• A Spoken Dialog Q A System
• Large Text Knowledge Base
• Learning Surface
• Text Patterns
• Question Answering System
• A GRAMMAR
• A LEXICON FOR A TEXT PRODUCTION SYSTEM
• Christian M
• Matthiessen
• THE CONTRIBUTION OF PARSING TO PROSODIC PHRASING IN
• EXPERIMENTAL TEXT TO SPEECH SYSTEM
• Joan Bachenko Eileen Fitzpatrick
• Automatic 3D Text to Scene Conversion System
• Road Accident Reports
• Ola Akerbergt Hans
• FOCUS AND ACCENT
• DUTCH TEXT TO SPEECH SYSTEM
• Joan LG
• Baart
• AN EXPERT SYSTEM
• THE PRODUCTION OF PHONEME STRINGS FROM UNMARKED ENGLISH TEXT
• MACHINE INDUCED RULES
• Smoking cessation
• SMS texting
• Implementing text messaging system
• Smokers in Hanoi
• Genetic Computer
• Knowledge Base System
• System Guide
• communication
• Computer tips
• text layout
• Wheaters functional histology
• Circulatory  system
• Skeletal tissues
• Immune system
• Central nervous system
• Special sense organs
• Oracle XSQL
• Oracle Text
• Publish Dynamic Web Content
• management system
• relational database
• Standard Query Language
• The cell
• Epithelium and glands
• Connective tissue
• Cartilage and bone
• Blood and hemopoiesis
• Muscle muscle
• Circulatory system
• Lymphoid tissue
• Corporate and business law
• Study text 2016
• Business law
• Essential elements
• Legal system
• Employmet law