TAILIEUCHUNG - Báo cáo khoa học: "Automatic learning of textual entailments with cross-pair similarities"

In this paper we define a novel similarity measure between examples of textual entailments and we use it as a kernel function in Support Vector Machines (SVMs). This allows us to automatically learn the rewrite rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of over the state-of-the-art methods. | Automatic learning of textual entailments with cross-pair similarities Fabio Massimo Zanzotto DISCo University of Milano-Bicocca Milan Italy zanzotto@ Alessandro Moschitti Department of Computer Science University of Rome Tor Vergata Rome Italy moschitti@ Abstract In this paper we define a novel similarity measure between examples of textual entailments and we use it as a kernel function in Support Vector Machines SVMs . This allows us to automatically learn the rewrite rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of over the state-of-the-art methods. 1 Introduction Recently textual entailment recognition has been receiving a lot of attention. The main reason is that the understanding of the basic entailment processes will allow us to model more accurate semantic theories of natural languages Chierchia and McConnell-Ginet 2001 and design important applications Dagan and Glickman 2004 . Question Answering and Information Extraction. However previous work . Zaenen et al. 2005 suggests that determining whether or not a text T entails a hypothesis H is quite complex even when all the needed information is explicitly asserted. For example the sentence T1 At the end of the year all solid companies pay dividends. entails the hypothesis H1 At the end of the year all solid insurance companies pay dividends. but it does not entail the hypothesis H2 At the end of the year all solid companies pay cash dividends. Although these implications are uncontrover-sial their automatic recognition is complex if we rely on models based on lexical distance or similarity between hypothesis and text . Corley and Mihalcea 2005 . Indeed according to such approaches the hypotheses Hl and H2 are very similar and seem to be similarly related to T1. This suggests that we should study the properties and differences of such two examples negative and positive to

• Báo cáo khoa học
• Automatic learning
• textual entailments
• cross pair similarities
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Journal of technology and science education
• Improving the learning experience of business subjects
• Engineering studies using automatic spreadsheet correctors
• Automatic spreadsheet correctors
• The field work
• International Journal of Computer Networks and Communications Security
• Adaptive e learning system based on learning interactivity
• Adaptive e learning system
• Clustering and adpative Elearning
• Automatic adapted trust relationship
• Semi supervised Learning
• Automatic Prosodic Event Detection
• Co training Algorithm
• báo cáo ngôn ngữ
• A Supervised Learning
• Approach to Automatic Synonym Identification
• Distributional Features
• A machine learning
• the automatic evaluation
• machine translation
• WORD TRANSDUCERS FROM EXAMPLES
• Michel Gilloux
• scientific reports
• model language
• process natural language
• Machine Learning Algorithms
• Deep Belief Network
• Restricted Boltzmann Machine
• Support Vector Machine
• Automatic CNC program
• Automatic modulation classification
• Deep learning
• Convolutional neural network
• Ensemble learning
• CNN models
• Automatic evaluation of practices
• Moodle for Self Learning in Engineering
• Moodle for Self Learning
• Exercises outside the classroom
• Automatic generation system
• Multiple choice cloze questions
• Statistical learning
• Preference learning
• Ranking voted perceptron
• Conditional random field
• BMC Bioinformatics
• Endogenous small
• Pre miRNAs
• Animal miRNAs systems
• Journal of science
• Learner content interaction
• English learning course at a Vietnamese university
• English learning course
• Automatic speech recognition
• Infancy like Vietnam
• Providing continuous technical support
• Synapse detection
• Automatic quantification
• 3D confocal image
• Model selection
• Environmental sciences
• Earth sciences
• Optical Remote Sensing
• Landsat 8 OLI
• Automatic cloud detection
• Open Data Cube
• PPE detection
• Object detection
• Automatic monitoring
• Real time personal protective equipment detection
• Fungal strains
• Dye decolorisation
• Image analysis
• Transfer learning
• Global and dynamic student modeling
• Dynamic student modeling
• Ubiquitous learning environment
• Student modeling
• Ubiquitous learning
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• BMC Genomics
• Antimicrobial resistance
• Antimicrobial peptide
• Feature fusion
• Organisms against microbes
• Instance segmentation
• Head circumference
• Mask RCNN
• Segmentation system
• Precision farming
• Internet of Robotic Things
• Suitable robot design
• Plankton classification
• Image classification
• Multiple view features
• Feature selection
• Multiple kernel learning
• Annotation of lecture videos
• Multimedia driven pedagogical platforms
• Intelligent tutoring systems
• Media in education
• Interactive learning environment
• Dinucleotide conformation
• Machine learning
• Neural network
• Regularized regression
• Cluster analysis