TAILIEUCHUNG - Báo cáo khoa học: "An Empirical Study of Chinese Chunking"

In this paper, we describe an empirical study of Chinese chunking on a corpus, which is extracted from UPENN Chinese Treebank-4 (CTB4). First, we compare the performance of the state-of-the-art machine learning models. Then we propose two approaches in order to improve the performance of Chinese chunking. 1) We propose an approach to resolve the special problems of Chinese chunking. This approach extends the chunk tags for every problem by a tag-extension function. 2) We propose two novel voting methods based on the characteristics of chunking task. Compared with traditional voting methods, the proposed voting methods consider long distance. | An Empirical Study of Chinese Chunking Wenliang Chen Yujie Zhang Hitoshi Isahara Computational Linguistics Group National Institute of Information and Communications Technology 3-5 Hikari-dai Seika-cho Soraku-gun Kyoto Japan 619-0289 chenwl yujie isahara @ Abstract In this paper we describe an empirical study of Chinese chunking on a corpus which is extracted from UPENN Chinese Treebank-4 CTB4 . First we compare the performance of the state-of-the-art machine learning models. Then we propose two approaches in order to improve the performance of Chinese chunking. 1 We propose an approach to resolve the special problems of Chinese chunking. This approach extends the chunk tags for every problem by a tag-extension function. 2 We propose two novel voting methods based on the characteristics of chunking task. Compared with traditional voting methods the proposed voting methods consider long distance information. The experimental results show that the SVMs model outperforms the other models and that our proposed approaches can improve performance significantly. 1 Introduction Chunking identifies the non-recursive cores of various types of phrases in text possibly as a precursor to full parsing or information extraction. Steven P. Abney was the first person to introduce chunks for parsing Abney 1991 . Ramshaw and Marcus Ramshaw and Marcus 1995 first represented base noun phrase recognition as a machine learning problem. In 2000 CoNLL-2000 introduced a shared task to tag many kinds of phrases besides noun phrases in English Sang and Buchholz 2000 . Additionally many machine learning approaches such as Support Vector Machines SVMs Vapnik 1995 Conditional Random Fields CRFs Lafferty et al. 2001 Memory-based Learning MBL Park and Zhang 2003 Transformation-based Learning TBL Brill 1995 and Hidden Markov Models HMMs Zhou et al. 2000 have been applied to text chunking Sang and Buchholz 2000 Hammerton et al. 2002 . Chinese chunking is a difficult task and much work has

• Báo cáo khoa học
• An Empirical Study
• Chinese Chunking
• Wenliang Chen
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Interactive control capability
• effective organizational learning and firm performance
• Empirical study of milling and metal industry in Tegal
• Empirical study of milling
• Metal industry in Tegal
• Economic growth
• Macro variables
• Macro variables in india
• The empirical linkages
• Strategic knowledge management
• Innovation and firm performance
• Firm performance
• Study in Vietnamese firms
• Master of Business Administration
• Business Administration
• Effective value chain management
• Empirical case study
• Public and Private Schools
• research
• design
• empirical
• study
• acquisition
• dod
• statutory
• regulatory
• constraints
• measuring
• A Combination of Active Learning
• Semi supervised Learning Starting
• Positive and Unlabeled Examples for Word Sense Disambiguation An Empirical Study on Japanese Web Search Query
• báo cáo ngôn ngữ
• An Extensive Empirical Study
• Collocation Extraction Methods
• Pavel Pecina
• Information Synthesis Tasks
• Enrique Amig
• An Empirical Study of the Influence
• Argument Conciseness
• Argument Effectiveness
• Exploiting Parallel Texts
• Word Sense Disambiguation
• An Empirical Study of Active Learning
• Support Vector Machines
• Japanese Word Segmentation
• THEMATIC KNOWLEDGE ACQUISITION
• SYNTACTIC CLUES AND HEURISTICS
• Empirical Study of Predictive Powers
• Simple Attachment Schemes
• Post modifier Prepositional Phrases
• scientific reports
• model language
• process natural language
• Class based Word
• Sense Disambiguation
• Lead lag relationship between spot
• Futures markets in three developing
• South East Asian countries Malaysia
• Lead lag relationship
• Spot and future markets
• Intra organizational
• Knowledge transfer Firm Performance
• Vietnam’s information technology companies
• Technology companies
• Forecasting energy intensity
• Fourier residual modified grey model
• An empirical study in Taiwan
• Absolute percentage error
• Forecast the energy intensity
• Empirical study on predictors
• Green sustainable software practices in Malaysian electronic industries
• Malaysian electronic industries
• Implementing sustainable software practice applications
• Influence sustainable software
• The impact of question structure
• Recipient attitude during
• Knowledge sharing
• Question response structure
• Growing the intention
• To adopt educational innovations
• Educational innovations
• Open access to learning
• Evaluation and evolution
• Bank efficiency considering heterogeneity technology
• Empirical study from China
• Dagum Gini index
• Kernel density estimation methods
• Empirical study of servqual
• Service quality measurement
• Highlight the implication of SERVQUAL
• Quality management approaches
• Manage services effectively and efficiently
• Customer oriented business philosophies
• Sustainable development
• Environmental accounting
• Sustainable development empirical study
• Overall results summary
• Repayment behavior
• Default position
• Credit availed farmers
• Default position of credit availed farmers
• Empirical study from Nayagarh district