TAILIEUCHUNG - Báo cáo khoa học: "Semantic Parsing with Bayesian Tree Transducers"

Many semantic parsing models use tree transformations to map between natural language and meaning representation. However, while tree transformations are central to several state-of-the-art approaches, little use has been made of the rich literature on tree automata. This paper makes the connection concrete with a tree transducer based semantic parsing model and suggests that other models can be interpreted in a similar framework, increasing the generality of their contributions. | Semantic Parsing with Bayesian Tree Transducers Bevan Keeley Jones Mark Johnson Sharon Goldwater sgwater@ School of Informatics University of Edinburgh Edinburgh EH8 9AB Uk t Department of Computing Macquarie University Sydney NSW 2109 Australia Abstract Many semantic parsing models use tree transformations to map between natural language and meaning representation. However while tree transformations are central to several state-of-the-art approaches little use has been made of the rich literature on tree automata. This paper makes the connection concrete with a tree transducer based semantic parsing model and suggests that other models can be interpreted in a similar framework increasing the generality of their contributions. In particular this paper further introduces a variational Bayesian inference algorithm that is applicable to a wide class of tree transducers producing state-of-the-art semantic parsing results while remaining applicable to any domain employing probabilistic tree transducers. 1 Introduction Semantic parsing is the task of mapping natural language sentences to a formal representation of meaning. Typically a system is trained on pairs of natural language sentences NLs and their meaning representation expressions MRs as in figure 1 a and the system must generalize to novel sentences. Most semantic parsing models rely on an assumption of structural similarity between MR and NL. Since strict isomorphism is overly restrictive this assumption is often relaxed by applying transformations. Several approaches assume a tree structure to the NL MR or both Ge and Mooney 2005 Kate and Mooney 2006 Wong and Mooney 2006 Lu et al. 2008 Borschinger et al. 2011 and often in- a Sentence what is the population of portland maine Meaning answer population cityid portland maine Jb answer population cityid 2 Portland maine what is the population of portland main C ợớ qo .answer Xj -t what is qpxi qi .population

• Báo cáo khoa học
• Semantic Parsing
• Bayesian Tree Transducers
• Bevan Keeley Jones
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Mapping between Compositional Semantic Representations
• Lexical Semantic Resources
• Towards Accurate Deep Semantic Parsing
• xử lý ngôn ngữ tự nhiên
• Joint Syntactic
• Semantic Parsing of Chinese
• Junhui Li and Guodong Zhou
• Semantics Driven Shallow Parsing
• Chinese Semantic Role Labeling
• Weiwei Sun
• Confidence Driven Unsupervised Semantic Parsing
• Dan Goldwasser
• Long Papers
• Semi Supervised
• Frame Semantic Parsing
• Unknown Predicates
• A Bayesian Model
• Unsupervised Semantic Parsing
• Ivan Titov Saarland
• Improving Dependency Parsing
• Semantic Classes
• Eneko Agirre
• An Ensemble Model
• Combines Syntactic and Semantic Clustering
• Discriminative Dependency Parsing
• The Task
• State of the Art and the Future
• Discriminative Reranking
• Ruifang Ge Raymond J
• Mooney
• mô hình ngôn ngữ
• Learning Synchronous Grammars
• Lambda Calculus
• Structured SVM Ensemble
• Classification Models
• A Study on Convolution Kernels
• Shallow Semantic Parsing
• Alessandro Moschitti
• Semantic Caseframe Parsing
• Syntactic Generality
• Philip J
• Hayes
• scientific reports
• model language
• process natural language
• A Logic of Semantic Representations
• Shallow Parsing
• Alexander Koller
• BMC Bioinformatics
• Biodiversity informatics
• Scientific name
• Semantic parser
• Parsing Expression Grammar
• Names based cyberinfrastructure
• Speech and language processing
• Natural language processing
• Computational linguistics
• Speech recognition
• Dependency parsing
• Automatic speech recognition
• Semantic role labeling