TAILIEUCHUNG - Báo cáo khoa học: "A Machine Learning Approach to Extract Temporal Information from Texts in Swedish and Generate Animated 3D Scenes"

Carsim is a program that automatically converts narratives into 3D scenes. Carsim considers authentic texts describing road accidents, generally collected from web sites of Swedish newspapers or transcribed from hand-written accounts by victims of accidents. One of the program’s key features is that it animates the generated scene to visualize events. To create a consistent animation, Carsim extracts the participants mentioned in a text and identifies what they do. | A Machine Learning Approach to Extract Temporal Information from Texts in Swedish and Generate Animated 3D Scenes Anders Berglund Richard Johansson Pierre Nugues Department of Computer Science LTH Lund University SE-221 00 Lund SWeden d98ab@ richard pierre @ Abstract Carsim is a program that automatically converts narratives into 3D scenes. Carsim considers authentic texts describing road accidents generally collected from web sites of Swedish newspapers or transcribed from hand-written accounts by victims of accidents. One of the program s key features is that it animates the generated scene to visualize events. To create a consistent animation Carsim extracts the participants mentioned in a text and identifies what they do. In this paper we focus on the extraction of temporal relations between actions. We first describe how we detect time expressions and events. We then present a machine learning technique to order the sequence of events identified in the narratives. We finally report the results we obtained. 1 Extraction of Temporal Information and Scene Visualization Carsim is a program that generates 3D scenes from narratives describing road accidents Johansson et al. 2005 Dupuy et al. 2001 . It considers authentic texts generally collected from web sites of Swedish newspapers or transcribed from handwritten accounts by victims of accidents. One of Carsim s key features is that it animates the generated scene to visualize events described in the narrative. The text below a newspaper article with its translation into English illustrates the goals and challenges of it. We bracketed the entities time expressions and events and we annotated them with identifiers denoted respectively Oi tj and ek En bussolycka e1 i sodra Afghanistan kravdee2 pả torsdagen t1 20 dodsoffer o1. Ytterligare 39 personer o2 skadadese3 i olyckane4. Busseno3 var pả vag e5 fran Kandahar mot huvudstaden Kabul nar deno4 under en omkorninge6 kordee7 av vagbanano5 och .

• Báo cáo khoa học
• A Machine Learning
• Extract Temporal Information
• Texts in Swedish
• Generate Animated 3D Scenes
• scientific reports
• model language
• process natural language
• Machine learning
• Lecture Machine learning
• Machine learning algorithms
• Data analysis methods
• Max margin learning
• Multi instance learning
• Reinforcement learning
• Delayed rewards
• Machine Learning Introduction
• Machine Learning Work
• Types of Machine Learning
• Supervised Learning
• Forms of Supervised Learning
• Bayesian Learning
• Back propagation
• Boltzmann machines
• Linear prediction
• Linear regression models
• Maximum likelihood
• Gaussian distributions
• Nonlinear ridge regression risk
• Cross validation
• Newton’s algorithm
• Gradient descent algorithm
• Logistic regression
• Logistic regression likelihood
• Formulate layers
• Neural networks
• Artificial neural networks
• Convolutional neural networks
• Design convolutional layers
• Recurrent nets
• Recurrent neural networks
• Lecture Introduction to Machine learning and Data mining
• Bài giảng Học máy và khai phá dữ liệu
• Machine learning and data mining
• Linear regression
• Learning a regression function
• Unsupervised learning
• Partition based clustering
• The sewing machine classroom
• Learning the ins
• Outs of your machine
• Mastering the materials
• Demystifying your machine
• Increasing your sphere
• Deep Belief Network
• Restricted Boltzmann Machine
• Support Vector Machine
• Automatic CNC program
• Challenges in Machine Learning
• Data Mining
• Learning from non vectorial data
• Beyond classification and regression
• Distributed data mining
• Machine learning bottleneck
• Introduction to machine learning
• Bayesian decision theory
• Parametric methods
• Multivariate methods
• BMC Bioinformatics
• Extreme learning machine
• Correntropy induced loss
• Machine learning method
• K nearest neighbors
• Neighbor based learnin
• Decision tree
• Random forest
• Support vector machines
• Separating hyperplane
• Artificial neural network
• Rectified linear unit
• Normalization methods
• Deep learning
• Representation learning
• Phenotype prediction
• Molecular diagnostics