TAILIEUCHUNG - Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling"

This paper presents a dependency language model (DLM) that captures linguistic constraints via a dependency structure, ., a set of probabilistic dependencies that express the relations between headwords of each phrase in a sentence by an acyclic, planar, undirected graph. Our contributions are three-fold. First, we incorporate the dependency structure into an n-gram language model to capture long distance word dependency. Second, we present an unsupervised learning method that discovers the dependency structure of a sentence using a bootstrapping procedure. . | Unsupervised Learning of Dependency Structure for Language Modeling Jianfeng Gao Microsoft Research Asia 49 Zhichun Road Haidian District Beijing 100080 China jfgao@ Abstract This paper presents a dependency language model DLM that captures linguistic constraints via a dependency structure . a set of probabilistic dependencies that express the relations between headwords of each phrase in a sentence by an acyclic planar undirected graph. Our contributions are three-fold. First we incorporate the dependency structure into an n-gram language model to capture long distance word dependency. Second we present an unsupervised learning method that discovers the dependency structure of a sentence using a bootstrapping procedure. Finally we evaluate the proposed models on a realistic application Japanese Kana-Kanji conversion . Experiments show that the best DLM achieves an error rate reduction over the word trigram model. 1 Introduction In recent years many efforts have been made to utilize linguistic structure in language modeling which for practical reasons is still dominated by trigram-based language models. There are two major obstacles to successfully incorporating linguistic structure into a language model 1 capturing longer distance word dependencies leads to higher-order n-gram models where the number of parameters is usually too large to estimate 2 capturing deeper linguistic relations in a language model requires a large annotated training corpus and a decoder that assigns linguistic structure which are not always available. This paper presents a new dependency language model DLM that captures long distance linguistic constraints between words via a dependency Hisami Suzuki Microsoft Research One Microsoft Way Redmond WA 98052 USA hisamis@ structure . a set of probabilistic dependencies that capture linguistic relations between headwords of each phrase in a sentence. To deal with the first obstacle mentioned above we .

• Báo cáo khoa học
• Unsupervised Learning
• Dependency Structure
• Language Modeling
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Learning Condensed Feature Representations
• Large Unsupervised Data Sets
• Supervised Learning
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Semantic Relation Composition
• Eduardo Blanco and Dan Moldovan
• Unsupervised co learning
• downward entailing operators
• Cristian Danescu
• Narrative Schemas and their Participants
• Nathanael Chambers and Dan Jurafsky
• Unsupervised Multilingual Learning
• Morphological Segmentation
• Benjamin Snyder and Regina Barzilay
• Narrative Event Chains
• Analyzing the Errors
• Percy Liang Dan Klein
• Unsupervised Learning of Acoustic
• Sub word Units
• Balakrishnan Varadarajan
• Supervised
• Sentence Compression
• Field Segmentation Models
• Information Extraction
• Annealing Techniques
• Unsupervised Statistical Language Learning
• Noah A
• Smith and Jason Eisner
• Unsupervised Learning of Arabic Stemming
• a Parallel Corpus
• Monica Rogati Scott McCarley Yiming Yang
• Unsupervised Learning – Clustering
• Partitional clustering
• Hierarchical clustering
• Expectation Maximization (EM) algorithm
• Incremental Clustering
• k Means algorithm
• Multi criteria decision making
• Combinative distance based
• Indian banks
• Hybrid unsupervised learning
• Multi criteria decision making approach
• Public sector banks
• Combinative Distance based Assessment
• K Means Clustering Performance
• BMC Bioinformatics
• Cell detection
• Deep learning
• Semi supervised learning
• Unsupervised domain adaptation
• Generalization capabilities
• Animal behavior
• Shape matching
• Shape context
• Active shape model
• Social sciences and humanities
• Self reported experiences
• Corruption on twitter
• Unsupervised machine learning
• Natural language processing
• Lecture Introduction to Machine learning and Data mining
• Bài giảng Học máy và khai phá dữ liệu
• Machine learning and data mining
• Partition based clustering
• Glioblastoma multiforme
• Deep belief network
• Gene expression
• Model selection
• Machine learning
• Unsupervised clustering
• Hyperparameter optimization
• Scikit learn
• Recommendation system
• Personalized web search
• Reinforcement learning
• Cooperative learning
• Probability
• random variables
• Joint probability
• discrete distributions
• Environmental advances
• Environmental contaminant mixtures
• Thyroid hormones
• Machine learning techniques
• Principal component analysis