TAILIEUCHUNG - Báo cáo khoa học: "A Bayesian Model for Discovering Typological Implications"

A standard form of analysis for linguistic typology is the universal implication. These implications state facts about the range of extant languages, such as “if objects come after verbs, then adjectives come after nouns.” Such implications are typically discovered by painstaking hand analysis over a small sample of languages. We propose a computational model for assisting at this process. Our model is able to discover both well-known implications as well as some novel implications that deserve further study. Moreover, through a careful application of hierarchical analysis, we are able to cope with the well-known sampling problem: languages are not. | A Bayesian Model for Discovering Typological Implications Hal Daume III School of Computing University of Utah me@ Lyle Campbell Department of Linguistics University of Utah lcampbel@ Abstract A standard form of analysis for linguistic typology is the universal implication. These implications state facts about the range of extant languages such as if objects come after verbs then adjectives come after nouns. Such implications are typically discovered by painstaking hand analysis over a small sample of languages. We propose a computational model for assisting at this process. Our model is able to discover both well-known implications as well as some novel implications that deserve further study. Moreover through a careful application of hierarchical analysis we are able to cope with the well-known sampling problem languages are not independent. 1 Introduction Linguistic typology aims to distinguish between logically possible languages and actually observed languages. A fundamental building block for such an understanding is the universal implication Greenberg 1963 . These are short statements that restrict the space of languages in a concrete way for instance object-verb ordering implies adjective-noun ordering Croft 2003 Hawkins 1983 and Song 2001 provide excellent introductions to linguistic typology. We present a statistical model for automatically discovering such implications from a large typological database Haspelmath et al. 2005 . Analyses of universal implications are typically performed by linguists inspecting an array of 30100 languages and a few pairs of features. Looking 65 at all pairs of features typically several hundred is virtually impossible by hand. Moreover it is insufficient to simply look at counts. For instance results presented in the form verb precedes object implies prepositions in 16 19 languages are nonconclusive. While compelling this is not enough evidence to decide if this is a statistically well-founded .

• Báo cáo khoa học
• A Bayesian Model
• Discovering Typological Implications
• Hal Daum
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Bayesian Network
• a model for NLP
• Davy Weissenbacher
• scientific reports
• model language
• process natural language
• Fuzzy discretization technique for bayesian flood disaster model
• Fuzzy discretization technique
• Flood disaster model
• Mitigate flood events
• Decision makers to perform actions
• Information sciences
• Semiparametric bayesian networks
• Kernel density estimation
• Semiparametric model
• Bayesian networks
• A Nonparametric Bayesian Approach
• Acoustic Model Discovery
• Chia ying Lee and Jame
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Unsupervised Semantic Parsing
• Ivan Titov Saarland
• A Hierarchical Bayesian
• Language Model
• Pitman Yor Processes
• Unsupervised Coreference Resolution
• Nonparametric Bayesian Model
• Aria Haghighi and Dan Klein
• A Dynamic Bayesian Framework
• Model Context and Memory in Edit Distance Learning
• An Application to Pronunciation Classification
• Identifying Agreement
• Disagreement in Conversational Speech
• Use of Bayesian Networks to Model Pragmatic Dependencies
• Bayesian model averaging
• Economic growth
• Public expenditure
• Explanatory variables included
• Economic theory
• Bayesian multilevel generalized linear model
• Economic growth rate
• Sustainable economic growth
• Higher per capita income
• Worldwide governance indicators
• BMC Bioinformatics
• Random effects model
• Bayesian random effects model
• Meta analysis
• Study heterogeneity
• Gene expression
• Sample quality weights
• Alzheimer’s disease
• Bayesian hierarchical model
• Data integration
• Dirichlet multinomial
• Microbiome data
• Variable selection
• RNA Seq
• Model based
• Multiple genes
• Small RNA fragments
• Bayesian classifier
• Two dimensional polyacrylamide gel electrophoresis
• Global Bayesian model
• Differentially expressed protein
• Markov chain Monte Carlo
• Highest posterior density
• Public health
• Integrated nested laplace approximation
• Latent gaussian model
• Identifying risk factors
• An Unsupervised Dynamic
• Measuring Speech Style Accommodation
• Bayesian Word Sense Induction
• Samuel Brody
• Long Papers
• Hierarchical Bayesian
• Language Modelling
• the Linguistically Informed
• A Bayesian Approach
• Unsupervised Semantic
• Role Induction
• Akaike information criteria
• Bayesian information criterion
• Vuongs test
• Poisson regression
• Zeroinated poisson regression
• Negative binomial regression
• Influence diagrams
• Bayesian networks and influence diagrams
• A guide to construction
• Eliciting the model
• Data driven modeling
• BMC Cancer
• Bayesian analysis
• Skeletal metastasis
• Prognostic model
• Postoperative survival
• Original tripartite network
• Item based collaborative filtering
• Updated tripartite network
• Naïve Bayesian classifier