TAILIEUCHUNG - Báo cáo khoa học: "Using Machine Learning to Explore Human Multimodal Clarification Strategies"

We investigate the use of machine learning in combination with feature engineering techniques to explore human multimodal clarification strategies and the use of those strategies for dialogue systems. We learn from data collected in a Wizardof-Oz study where different wizards could decide whether to ask a clarification request in a multimodal manner or else use speech alone. We show that there is a uniform strategy across wizards which is based on multiple features in the context. These are generic runtime features which can be implemented in dialogue systems. . | Using Machine Learning to Explore Human Multimodal Clarification Strategies Verena Rieser Department of Computational Linguistics Saarland University Saarbrucken D-66041 vrieser@ Oliver Lemon School of Informatics University of Edinburgh Edinburgh EH8 9LW Gb olemon@ Abstract We investigate the use of machine learning in combination with feature engineering techniques to explore human multimodal clarification strategies and the use of those strategies for dialogue systems. We learn from data collected in a Wizard-of-Oz study where different wizards could decide whether to ask a clarification request in a multimodal manner or else use speech alone. We show that there is a uniform strategy across wizards which is based on multiple features in the context. These are generic runtime features which can be implemented in dialogue systems. Our prediction models achieve a weighted f-score of which is a improvement over a one-rule baseline . To assess the effects of models feature discretisation and selection we also conduct a regression analysis. We then interpret and discuss the use of the learnt strategy for dialogue systems. Throughout the investigation we discuss the issues arising from using small initial Wizard-of-Oz data sets and we show that feature engineering is an essential step when learning from such limited data. 1 Introduction Good clarification strategies in dialogue systems help to ensure and maintain mutual understanding and thus play a crucial role in robust conversational interaction. In dialogue application domains with high interpretation uncertainty for example caused by acoustic uncertainties from a speech recogniser multimodal generation and input leads to more robust interaction Oviatt 2002 and re duced cognitive load Oviatt et al. 2004 . In this paper we investigate the use of machine learning ML to explore human multimodal clarification strategies and the use of those strategies to decide based on the current .

• Báo cáo khoa học
• Using Machine Learning
• Explore Human Multimodal
• Clarification Strategies
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Oral cancer prognosis
• Machine learning techniques
• Feature selection
• Machine learning
• Handling noisy
• Nonlinear autoregressive
• Long short term Memory
• Based on the available data
• Content classification
• Comment classification
• Using supervised machine learning
• Machine learning method
• Neural network
• Decision tree
• Environmental advances
• Environmental contaminant mixtures
• Thyroid hormones
• Principal component analysis
• Techniques to Build
• Comma Checker for Basque
• Assign Function Labels
• Parser Output for Spanish
• Extracting Comparative Sentences
• Korean Text Documents Using Comparative Lexical Patterns
• báo cáo ngôn ngữ
• Using Emoticons to reduce Dependency
• Sentiment Classification
• Using Machine Learning to Maintain Rule based Named Entity Recognition
• Classification Systems
• Georgios Petasis
• Techniques to Interpret WH questions
• Ingrid Zukerman
• BMC Bioinformatics
• RNA Seq
• Statistical learning
• Quantifying gene
• Extreme learning machine
• Artificial chemical reaction optimization algorithm
• Single hidden layer feed forward neural network
• Learning algorithm
• BMC Cancer
• Esophageal squamous cell carcinoma
• Support vector machine
• Random forest
• Logical regression
• Artificial neural network
• Paraphrase Recognition
• Combine Similarity Measures
• Trimming CFG Parse Trees
• Sentence Compression
• Machine Learning Approaches
• Extraction of definitions
• grammar enhanced machine learning
• Long Papers
• scientific reports
• model language
• process natural language
• Vehicle detection
• Background subtraction
• Optical flow
• Kalman filters
• Credit scoring
• Vietnamese commercial banks
• Big data
• Artificial intelligence
• Genome wide association
• GWAS techniques
• Age related macular degeneration
• Small ORF
• Vital biological activities
• Normal proteins
• Fanconi anemia
• Signaling pathways
• Mathematical models
• Metabolic syndrome
• Integration of metabolomics
• Non small cell lung cancer
• Drug repositioning
• Microarray data analysis
• Machine learning algorithm
• Topological parameters
• Protein protein interactions
• Substance use disorders
• Cocaine dependence
• Support vector machines