TAILIEUCHUNG - Báo cáo khoa học: "Word Sense Disambiguation vs. Statistical Machine Translation"

We directly investigate a subject of much recent debate: do word sense disambigation models help statistical machine translation quality? We present empirical results casting doubt on this common, but unproved, assumption. Using a state-ofthe-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone. . | Word Sense Disambiguation vs. Statistical Machine Translation Marine CARPUAT Dekai WU1 marine@ dekai@ Human Language Technology Center HKUST Department of Computer Science University of Science and Technology Clear Water Bay Hong Kong Abstract We directly investigate a subject of much recent debate do word sense disambiga-tion models help statistical machine translation quality We present empirical results casting doubt on this common but unproved assumption. Using a state-of-the-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system we find that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone. Error analysis suggests several key factors behind this surprising finding including inherent limitations of current statistical MT architectures. 1 Introduction Word sense disambiguation or WSD the task of determining the correct sense of a word in context is a much studied problem area with a long and honorable history. Recent years have seen steady accuracy gains in WSD models driven in particular by controlled evaluations such as the Senseval series of workshops. Word sense disambiguation is often assumed to be an intermediate task which should then help higher level applications such as machine 1The authors would like to thank the Hong Kong Research Grants Council RGC for supporting this research in part through grants RGC6083 99E RGC6256 00E and DAG03 and several anonymous reviewers for insights and suggestions. translation or information retrieval. However WSD is usually performed and evaluated as a standalone task and to date there have been very few efforts to integrate the learned WSD models into full statistical MT systems. An energetically debated question at conferences over the past year is whether even the new state-of-the-art word sense disambiguation models actually have anything to .

• Báo cáo khoa học
• Word Sense Disambiguation
• Statistical Machine Translation
• Marine CARPUAT
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• International Journal of Computer Science & Communication Networks
• Automatic word sense disambiguation using wikipedia link structure
• Automatic word sense disambiguation
• Wikipedia link structure
• It Makes Sense
• A Wide Coverage Word Sense Disambiguation System
• Free Text
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Word Sense Disambiguation Improves Information Retrieval
• Zhi Zhong and Hwee Tou Ng
• Long Papers
• Topic Models
• Token based Idiom Detection
• Knowledge rich Word Sense
• Disambiguation Rivaling Supervised Systems
• Simone Paolo Ponzetto
• Latent Semantic Word Sense Induction
• Disambiguation
• ParaSense
• How to Use Parallel Corpora
• Estimating Class Priors
• Domain Adaptation
• Meaningful Clustering of Senses
• Helps Boost Word Sense
• Disambiguation Performance
• An Equivalent Pseudoword Solution
• Chinese Word Sense Disambiguation
• Zhimao Lu
• 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
• lexical cohesion in the context
• Dongqiang Yang
• Improves Statistical
• Machine Translation
• Learning Expressive Models
• Lucia Specia
• Active Learning
• Label Propagation Based Semi Supervised Learning
• Zheng Yu Niu
• Dong Hong Ji
• Domain Kernels
• Alfio Gliozzo and Claudio Giuliano and Carlo Strapparava
• Learning Semantic Classes
• Upali S
• Kohomban Wee Sun Lee
• SenseLearner
• All Words in Unrestricted Text
• TargetWord
• A Generalized Framework
• Relieving The Data Acquisition Bottleneck
• Mona Diab
• A Kernel PCA Method
• Superior Word Sense Disambiguation
• Exploiting Parallel Texts
• An Empirical Study
• Pairwise Alignment
• Koichi Yamashita Keiichi Yoshida Yukihiro Itoh