TAILIEUCHUNG - Báo cáo khoa học: "Error Detection for Statistical Machine Translation Using Linguistic Features"

Automatic error detection is desired in the post-processing to improve machine translation quality. The previous work is largely based on confidence estimation using system-based features, such as word posterior probabilities calculated from N best lists or word lattices. We propose to incorporate two groups of linguistic features, which convey information from outside machine translation systems, into error detection: lexical and syntactic features. | Error Detection for Statistical Machine Translation Using Linguistic Features Deyi Xiong Min Zhang Haizhou Li Human Language Technology Institute for Infocomm Research 1 Fusionopolis Way 21-01 Connexis Singapore 138632. dyxiong mzhang hli @ Abstract Automatic error detection is desired in the post-processing to improve machine translation quality. The previous work is largely based on confidence estimation using system-based features such as word posterior probabilities calculated from N-best lists or word lattices. We propose to incorporate two groups of linguistic features which convey information from outside machine translation systems into error detection lexical and syntactic features. We use a maximum entropy classifier to predict translation errors by integrating word posterior probability feature and linguistic features. The experimental results show that 1 linguistic features alone outperform word posterior probability based confidence estimation in error detection and 2 linguistic features can further provide complementary information when combined with word confidence scores which collectively reduce the classification error rate by and improve the F measure by . 1 Introduction Translation hypotheses generated by a statistical machine translation SMT system always contain both correct parts . words n-grams phrases matched with reference translations and incorrect parts. Automatically distinguishing incorrect parts from correct parts is therefore very desirable not only for post-editing and interactive machine translation Ueffing and Ney 2007 but also for SMT itself either by rescoring hypotheses in the N -best list using the probability of correctness calculated for each hypothesis Zens and Ney 2006 or by generating new hypotheses using N-best lists from one SMT system or multiple sys tems Akibay et al. 2004 Jayaraman and Lavie 2005 . In this paper we restrict the parts to words. That is we detect errors at the word level

• Báo cáo khoa học
• Error Detection
• Statistical Machine Translation
• Linguistic Features
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Error Sources
• Detection and Correction
• Detectio9
• 2 Detection
• VRC
• Data
• OSI model
• Convolutional LSTM
• Convolutional autoencoder
• Prediction error
• Reconstruction error
• Anomaly detection
• viễn thông
• The Data Link Layer
• bài giảng viễn thông
• C
• Huang University of Houston
• Software Error Detection
• Testing and Analysis
• test case selection
• Software
• Correction
• Modular Arithmetic
• Versus Correction
• directly
• indirectly
• Using Parse Features
• Preposition Selection
• Using Crowdsourcing
• Improve the Evaluation
• Grammatical Error Detection Systems
• Using Derivation Trees
• Treebank Error Detection
• Seth Kulick
• Using Deep Morphology
• Improve Automatic Error Detection in Arabic Handwriting Recognition
• Nizar Habash and Ryan M
• Roth
• Using Generation for Grammar Analysis
• Michael Wayne
• xử lý ngôn ngữ tự nhiên
• Automatic error detection
• the Japanese learners’ English
• spoken data
• mô hình ngôn ngữ
• Bài giảng Mạng máy tính nâng cao
• Mạng máy tính nâng cao
• Mạng máy tính
• Link layer and LANs
• Error detection and correction
• Link layer addressing
• Error control
• Mobile computing
• Wireless and mobile computing
• Services data
• Wireless communication
• Journal of Automation and Control Engineering
• The total error limited by modifying the parameters
• Zernike moments computation in duplicated images
• Reducing Geometrical Error
• Tampered image detection
• Detection and Correctio
• LRC
• CRC Generation
• performance
• Computer Architecture
• dependability challenge
• fault tolerance
• Error Recovery
• Index modulation
• IM OFDM
• Coordinate interleaving
• Pair wise error probability
• Symbol error probability
• Maximum likelihood detection
• Nakagami m fading
• BMC Bioinformatics
• Next generation sequencing
• Variant calling
• Error suppression
• Single nucleotide variant
• Ultra deep next generation sequencing
• Illumina error prediction
• Local quality scores
• Position specific quality
• Non homogeneous Poisson process
• Software reliability growth model
• Mean square error
• Predictive ratio risk
• Predictive power
• Logistic fault detection rate
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo