TAILIEUCHUNG - Báo cáo khoa học: "Automatic Generation of Story Highlights"

In this paper we present a joint content selection and compression model for single-document summarization. The model operates over a phrase-based representation of the source document which we obtain by merging information from PCFG parse trees and dependency graphs. Using an integer linear programming formulation, the model learns to select and combine phrases subject to length, coverage and grammar constraints. | Automatic Generation of Story Highlights Kristian Woodsend and Mirella Lapata School of Informatics University of Edinburgh Edinburgh EH8 9AB United Kingdom mlap@ Abstract In this paper we present a joint content selection and compression model for single-document summarization. The model operates over a phrase-based representation of the source document which we obtain by merging information from PCFG parse trees and dependency graphs. Using an integer linear programming formulation the model learns to select and combine phrases subject to length coverage and grammar constraints. We evaluate the approach on the task of generating story highlights a small number of brief self-contained sentences that allow readers to quickly gather information on news stories. Experimental results show that the model s output is comparable to human-written highlights in terms of both grammaticality and content. 1 Introduction Summarization is the process of condensing a source text into a shorter version while preserving its information content. Humans summarize on a daily basis and effortlessly but producing high quality summaries automatically remains a challenge. The difficulty lies primarily in the nature of the task which is complex must satisfy many constraints . summary length informativeness coherence grammaticality and ultimately requires wide-coverage text understanding. Since the latter is beyond the capabilities of current NLP technology most work today focuses on extractive summarization where a summary is created simply by identifying and subsequently concatenating the most important sentences in a document. Without a great deal of linguistic analysis it is possible to create summaries for a wide range of documents. Unfortunately extracts are often documents of low readability and text quality and contain much redundant information. This is in marked contrast with hand-written summaries which often combine several pieces of .

• Báo cáo khoa học
• Automatic Generation
• Story Highlights
• Long Papers
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Many Words is a Picture Worth
• Automatic Caption Generation
• News Images
• Automatic Headline Generation
• Character Cross Correlation
• Fahad A
• Alotaiby
• Automatic Generation of Domain Models
• Call Centers
• Noisy Transcriptions
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Automatic Generation of Information seeking Questions
• Concept Clusters
• Shuguang L
• An Automatic Generation System
• Grammar Tests
• Chia Yin Chen
• Towards Web Based
• Evaluation of Automatic Natural Language
• Phrase Generation
• Automatic generation of short
• informative sentiment summaries
• Andrea Glaser
• scientific reports
• model language
• process natural language
• Automatic generation system
• Multiple choice cloze questions
• Statistical learning
• Preference learning
• Ranking voted perceptron
• Conditional random field
• Automatic test case generation
• Functional testing
• System testing
• Testing based on use case
• Specification language UCML
• BMC Bioinformatics
• Semantic web
• Ontology generation
• Linked open data
• Semantic enrichment
• Next generation sequencing
• Genome assembly
• Genome finishing
• Genome scaffolding
• Marine Synechococcus
• Question generation
• Collaborative argumentation
• Question generation system
• Adopting semantic information
• Automatic 3D Model Generation
• Adaptive Estimation and Control
• Adaptive output regulation
• Output Feedback Direct
• Discrete Model Matching Adaptive
• Hybrid Schemes for Adaptive Control Strategies
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• rajectory Generation
• Multi agent Systems
• Mobile robots
• Automatic Trajectory
• Control
• Geometric
• User Interfaces
• Case Models
• Interface Design
• PON Network
• Management System
• software systems
• fault diagnosis
• memory testing
• physical fault models
• automatic test pattern generation
• Hardware Testing
• Power Generation Systems
• Overview of ABWR Systems
• Nuclear Power Engineering
• Electric Power University
• Safety Systems of ABWR
• Automatic Depressurization System
• Khoa học máy tính
• Tạp chí khoa học
• Automatic test data generation
• Search based software testing
• Particle Swarm Optimization
• Phương pháp sinh tự động ca kiểm thử
• Mô hình ca sử dụng
• Đặc tả ca sử dụng
• Use Case Specification
• Automatic Test Generation
• Kịch bản kiểm thử ca sử dụng
• Readthrough transcription
• Transcription termination
• Gene expression
• Next generation sequencing analysis
• Multilingual corpus generation
• Statistical machine translation
• Biomedical domain
• Non native speakers
• Biomedical information