TAILIEUCHUNG - Báo cáo khoa học: "Learning Features that Predict Cue Usage"

Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program, , to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be. | Learning Features that Predict Cue Usage Barbara Di Eugenio Johanna D. Moore Massimo Paolucci University of Pittsburgh Pittsburgh PA 15260 USA dieugeni jmoore paolucci Abstract Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable US to identify the features with most predictive power and show that machine learning can be used to induce decision trees useful for text generation. 1 Introduction Discourse cues are words or phrases such as because first and although that mark structural and semantic relationships between discourse entities. They play a crucial role in many discourse processing tasks including plan recognition Litman and Allen 1987 text comprehension Cohen 1984 Hobbs 1985 Mann and Thompson 1986 Reichman-Adar 1984 and anaphora resolution Grosz and Sidner 1986 . Moreover research in reading comprehension indicates that felicitous use of cues improves comprehension and recall Goldman 1988 but that their indiscriminate use may have detrimental effects on recall Millis Graesser and Haberlandt 1993 . Our goal is to identify general strategies for cue usage that can be implemented for automatic text generation. From the generation perspective cue usage consists of three distinct but interrelated problems 1 occurrence- whether or not to include a cue in the generated text 2 placement where the cue should be placed in the text and 3 selection what lexical item s should be used. Prior work in text generation has focused on cue selection McKeown and Elhadad 1991 Elhadad and McKeown 1990 or on .

• Báo cáo khoa học
• Learning Features
• Predict Cue Usage
• Barbara
• scientific reports
• model language
• process natural language
• A foreign language
• Cultural features
• Linguistic features
• Learning English
• Teaching English
• English requests
• Accurate Learning
• Chinese Function Tags
• Minimal Features
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Learning More Effective
• Dialogue Strategies
• Limited Dialogue Move Features
• mô hình ngôn ngữ
• A Supervised Learning
• Approach to Automatic Synonym Identification
• Distributional Features
• Experiments on the Choice of Features
• Learning Verb Classes
• Sabine Schulte
• Multiple modal features
• Multiple kernel learning for human daily activity recognition
• Human daily activity recognition
• Activity recognition system
• Complex patterns of activity
• Learning Modernizr
• Adam Watson
• CSS3 features
• CSS based
• using feature detection features of Modernizr
• BMC Bioinformatics
• Plankton classification
• Image classification
• Multiple view features
• Feature selection
• Multiple kernel learning
• Grammatical features
• ESP grammar
• Specific purpose grammar
• Students’ difficulties in learning English
• neurotransmitter
• glutamate
• sufficiently many neurons
• Cryopreserved Semen
• Chemical Features
• Non Conventional Fruits
• Computer Vision
• Imagine processing
• Computer science
• Generative learning methods
• Generative methods
• Action recognition
• Genetic algorithm
• Multi label learning
• Human splicing branchpoint
• Logistic regression
• Deep convolution activation feature
• Deep learning
• Feature learning
• Histopathology image analysis
• Android malware classification
• Deep learning CNN with Co occurrence matrix feature
• Co occurrence matrix feature
• Co concurrence matrix
• Features of the malwares
• Information Science
• Machine learning approaches
• Environments on human’s physiological response
• Features selection
• Wearable devices
• Physiological data
• Protein glycosylation prediction
• Positive unlabelled learning
• Supervised learning
• Sequence analysis
• Sequence derived features
• Khoa học máy tính
• Tạp chí khoa học
• Author profiling
• Machine learning
• Content based features
• Non dictionary words
• Including stylometric features
• Essential genes
• Random Forest
• Information theoretic features
• English collocations
• Semantic features of English collocations
• Verb English
• International criminal documents
• Suggestions for learning
• equivalent to loosening
• investors represent
• Recent Trends
• Geopolymer Composite
• Fire Resistance
• Features and Applications
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• recruiting large
• tax breaks
• financial incentives
• complementary features
• develop and support
• small businesses