检索结果-内蒙古大学图书馆

CYK parsing over Distributed Representations

algorithms 2020年第10期13卷 262页

作者： Zanzotto, Fabio Massimo Satta, Giorgio Cristini, Giordano Univ Roma Tor Vergata Dept Enterprise Engn Viale Politecn 1 I-00133 Rome Italy Univ Padua Dept Informat Engn Via Gradenigo 6-A I-35131 Padua Italy Exprivia SpA Viale Tintoretto 432 I-00142 Rome Italy

parsing is a key task in computer science, with applications in compilers, natural language processing, syntactic pattern matching, and formal language theory. With the recent development of deep learning techniques, several artificial intelligence applications, especially in natural language processing, have combined traditional parsing methods with neural networks to drive the search in the parsing space, resulting in hybrid architectures using both symbolic and distributed representations. In this article, we show that existing symbolic parsing algorithms for context-free languages can cross the border and be entirely formulated over distributed representations. To this end, we introduce a version of the traditional Cocke-Younger-Kasami (CYK) algorithm, called distributed (D)-CYK, which is entirely defined over distributed representations. D-CYK uses matrix multiplication on real number matrices of a size independent of the length of the input string. These operations are compatible with recurrent neural networks. Preliminary experiments show that D-CYK approximates the original CYK algorithm. By showing that CYK can be entirely performed on distributed representations, we open the way to the definition of recurrent layer neural networks that can process general context-free languages.

关键词： parsing algorithms neural networks distributed representations formal languages

来源：评论

学校读者我要写书评

暂无评论

CONTEXT-SENSITIVE parsing

引用

COMMUNICATIONS OF THE ACM 1970年第7期13卷 437-&页

作者： WOODS, WA Harvard Univ. Cambridge MA

This paper presents a canonical form for context-sensitive derivations and a parsing algorithm which finds each context-sensitive analysis once and only once. The amount of memory required by the algorithm is essentially no more than that required to store a single complete derivation. In addition, a modified version of the basic algorithm is presented which blocks infinite analyses for grammars which contain loops. The algorithm is also compared with several previous parsers for context-sensitive grammars and general rewriting systems, and the difference between the two types of analyses is discussed. The algorithm appears to be complementary to an algorithm by S. Kuno in several respects, including the space-time trade-off and the degree of context dependence involved. [ABSTRACT FROM AUTHOR]

关键词： context-sensitive grammars context-sensitive parsing formal grammars formal language theory parsing parsing algorithms recognition algorithms

来源：评论

学校读者我要写书评

暂无评论

Image parsing via Stochastic Scene Grammar 11

Image Parsing via Stochastic Scene Grammar

引用

Annual Conference on Neural Information Processing Systems

作者： Yibiao Zhao Song-Chun Zhu Department of Statistics University of California Los Angeles Los Angeles CA 90095 Department of Statistics and Computer Science University of California Los Angeles Los Angeles CA 90095

ISBN: (纸本)9781618395993

This paper proposes a parsing algorithm for scene understanding which includes four aspects: computing 3D scene layout, detecting 3D objects (e.g. furniture), detecting 2D faces (windows, doors etc.), and segmenting background. In contrast to previous scene labeling work that applied discriminative classifiers to pixels (or super-pixels), we use a generative Stochastic Scene Grammar (SSG). This grammar represents the compositional structures of visual entities from scene categories, 3D foreground/background, 2D faces, to ID lines. The grammar includes three types of production rules and two types of contextual relations. Production rules: (i) AND rules represent the decomposition of an entity into sub-parts; (ii) OR rules represent the switching among sub-types of an entity; (iii) SET rules represent an ensemble of visual entities. Contextual relations: (i) Cooperative "+" relations represent positive links between binding entities, such as hinged faces of a object or aligned boxes; (ii) Competitive "-" relations represents negative links between competing entities, such as mutually exclusive boxes. We design an efficient MCMC inference algorithm, namely Hierarchical cluster sampling, to search in the large solution space of scene configurations. The algorithm has two stages: (i) Clustering: It forms all possible higher-level structures (clusters) from lower-level entities by production rules and contextual relations, (ii) Sampling: It jumps between alternative structures (clusters) in each layer of the hierarchy to find the most probable configuration (represented by a parse tree). In our experiment, we demonstrate the superiority of our algorithm over existing methods on public dataset. In addition, our approach achieves richer structures in the parse tree.

关键词： parsing tree syntax Rule Solution space Production Rule parsing algorithms DOOR parsing

来源：评论

学校读者我要写书评

暂无评论

Virtual Enterprise Synthesis by Web Services Composition with HTN-like parsing Algorithm (WIP) 15

Virtual Enterprise Synthesis by Web Services Composition wit...

引用

Simulation Multiconference

作者： Victor Romanov Ekaterina Yudakova Svetlana Efimova Aleksandra Varfolomeeva Russian Plekhanov University of Economics

ISBN: (纸本)9781510810594

The rapidly changing business environment dictates the need for enterprises to change their structures, processes and systems with the same speed in order to save clients and to remain competitive and compliant to the world around. The virtual enterprises provide such opportunity. Existence of a large number of various services in the Cloud does potentially possible both fast changing of the enterprise, and assembly of the new enterprises of atomic services. Automated planning algorithms are important part of such synthesis. In this paper, we suggest to apply the theory of the formal grammar and the appropriate procedures as means of automated planning support for web services composition.

关键词： Virtual Enterprise Synthesis Web Services Composition Automated Planning Formal Grammar HTN Planning Web Service Virtual enterprises Companies parsing algorithms Cloud Computing WIPF1 gene synthesis Legal Services customers

来源：评论

学校读者我要写书评

暂无评论

Exact Inference for Generative Probabilistic Non-Projective Dependency parsing 11

Exact Inference for Generative Probabilistic Non-Projective ...

引用

Conference on empirical methods in natural language processing

作者： Shay B. Cohen Carlos Gomez-Rodriguez Giorgio Satta Carnegie Mellon University Universidade da Coruña Spain University of Padua Italy

ISBN: (纸本)9781937284114

We describe a generative model for non-projective dependency parsing based on a simplified version of a transition system that has recently appeared in the literature. We then develop a dynamic programming parsing algorithm for our model, and derive an inside-outside algorithm that can be used for unsu-pervised learning of non-projective dependency trees.

关键词： parsing DEPENDENCE parsing algorithms Probability algorithms Literature Exact

来源：评论

学校读者我要写书评

暂无评论

Exemplar-Based Face parsing

Exemplar-Based Face Parsing

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Brandon M. Smith Li Zhang Jonathan Brandt Zhe Lin Jianchao Yang University of Wisconsin-Madison Adobe Research

ISBN: (纸本)9781467364102

In this work, we propose an exemplar-based face image segmentation algorithm. We take inspiration from previous works on image parsing for general scenes. Our approach assumes a database of exemplar face images, each of which is associated with a hand-labeled segmentation map. Given a test image, our algorithm first selects a subset of exemplar images from the database, Our algorithm then computes a non-rigid warp for each exemplar image to align it with the test image. Finally, we propagate labels from the exemplar images to the test image in a pixel-wise manner, using trained weights to modulate and combine label maps from different exemplars. We evaluate our method on two challenging datasets and compare with two face parsing algorithms and a general scene parsing algorithm. We also compare our segmentation results with contour-based face alignment results;that is, we first run the alignment algorithms to extract contour points and then derive segments from the contours. Our algorithm compares favorably with all previous works on all datasets evaluated.

关键词： test sample images Face Face parsing parsing algorithms Imagery (Psychotherapy) Image contour Database Dataset Respiratory Inspiration inspiration segmentation Outlines

来源：评论

学校读者我要写书评

暂无评论

Fast Exact Inference with a Factored Model for Natural Language parsing 02

Fast Exact Inference with a Factored Model for Natural Langu...

引用

Annual Conference on Neural Information Processing Systems

作者： Dan Klein Christopher D. Manning Department of Computer Science Stanford University Stanford CA 94305-9040

ISBN: (纸本)0262025507

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization provides conceptual simplicity, straightforward opportunities for separately improving the component models, and a level of performance comparable to similar, non-factored models. Most importantly, unlike other modern parsing models, the factored model admits an extremely effective A* parsing algorithm, which enables efficient, exact inference.

关键词： parsing Level of Performance PRINT Language Exact parsing algorithms TREE STRUCTURES

来源：评论

学校读者我要写书评

暂无评论

Creating collaboration instruments in the parametric design context

Creating collaboration instruments in the parametric design ...

引用

IABSE Conference, Bath 2017: Creativity and Collaboration - Instilling Imagination and Innovation in Structural Design

作者： Demin, Dimitry Dietrich, Sebastian Swiss Federal Institute of Technology Zürich Switzerland Bauhaus University Weimar Germany

This paper outlines the development of a new open-source plugin for collaboration workflow within the parametric design paradigm. Processes of informational exchange support the integration approaching workflows for p... 详细信息

关键词： Collaboration Finite element Parametric engineering parsing algorithms

来源：评论

学校读者我要写书评

暂无评论

NASA Technical Reports Server (Ntrs) 20070027745: Blurring the Inputs: a Natural Language Approach to Sensitivity Analysis

引用

2017年

NASA Technical Reports Server (Ntrs) 20070027745: Blurring the Inputs: a Natural Language Approach to Sensitivity Analysis by NASA Technical Reports Server (Ntrs); published by

关键词： (ntrs) 20070027745: analysis approach automation blurring central processing units computational fluid dynamics direct numerical simulation johnston, christopher o. kleb, william l. mathematical models monte carlo method nasa technical reports server (ntrs) natural language (computers) parsing algorithms reynolds averaging sensitivity analysis stagnation point thompson, richard a.

来源：评论

学校读者我要写书评

暂无评论

NASA Technical Reports Server (Ntrs) 20140012995: Ikos: a Framework for Static Analysis Based on Abstract Interpretation (Tool Paper)

引用

2016年

NASA Technical Reports Server (Ntrs) 20140012995: Ikos: a Framework for Static Analysis Based on Abstract Interpretation (Tool Paper) by NASA Technical Reports Server (Ntrs); NASA Technical Reports Server (Ntrs); publ... 详细信息

关键词： (ntrs) (tool 20140012995: abstract analysis avionics brat, guillaume p. certification computer programs flight control laserna, jorge a. management analysis nasa technical reports server (ntrs) parsing algorithms precision shi, nija software engineering venet, arnaud jean

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：