TAILIEUCHUNG - Báo cáo khoa học: "Dependency Parsing with Undirected Graphs"

We introduce a new approach to transitionbased dependency parsing in which the parser does not directly construct a dependency structure, but rather an undirected graph, which is then converted into a directed dependency tree in a post-processing step. This alleviates error propagation, since undirected parsers do not need to observe the single-head constraint. Undirected parsers can be obtained by simplifying existing transition-based parsers satisfying certain conditions. We apply this approach to obtain undirected variants of the planar and 2-planar parsers and of Covington’s non-projective parser. . | Dependency Parsing with Undirected Graphs Carlos Gomez-Rodriguez Departamento de Computation Universidade da Coruna Campus de Elvina 15071 A Coruna Spain Daniel Fernandez-Gonzalez Departamento de Informatica Universidade de Vigo Campus As Lagoas 32004 Ourense Spain danifg@ Abstract We introduce a new approach to transitionbased dependency parsing in which the parser does not directly construct a dependency structure but rather an undirected graph which is then converted into a directed dependency tree in a post-processing step. This alleviates error propagation since undirected parsers do not need to observe the single-head constraint. Undirected parsers can be obtained by simplifying existing transition-based parsers satisfying certain conditions. We apply this approach to obtain undirected variants of the planar and 2-planar parsers and of Covington s non-projective parser. We perform experiments on several datasets from the CoNLL-X shared task showing that these variants outperform the original directed algorithms in most of the cases. 1 Introduction Dependency parsing has proven to be very useful for natural language processing tasks. Data-driven dependency parsers such as those by Nivre et al. 2004 McDonald et al. 2005 Titov and Henderson 2007 Martins et al. 2009 or Huang and Sagae 2010 are accurate and efficient they can be trained from annotated data without the need for a grammar and they provide a simple representation of syntax that maps to predicateargument structure in a straightforward way. In particular transition-based dependency parsers Nivre 2008 are a type of dependency parsing algorithms which use a model that scores transitions between parser states. Greedy deterministic search can be used to select the transition to be taken at each state thus achieving linear or quadratic time complexity. 0 1 2 3 Figure 1 An example dependency structure where transition-based parsers enforcing the single-head constraint will incur .

• Báo cáo khoa học
• Dependency Parsing
• Undirected Graphs
• Workshops
• scientific reports
• model language
• process natural language
• Using distributed word representations
• Graph based dependency parsing for Vietnamese
• Graph based dependency parsing
• Dependency syntax
• Vietnamese syntax
• Vietnamese dependency parsing
• Utilizing Dependency Language Models
• Graph based Dependency Parsing Models
• Wenliang Chen
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Ependency parsing
• Cross lingual
• Low resource language
• Word order transformation
• Selective Sharing
• Multilingual Dependency Parsing
• Tahira Naseem
• Semi supervised Dependency Parsing
• Lexical Affinities
• Alexis Nasr
• Incremental Joint Approach
• Word Segmentation
• POS Tagging
• Dependency Hashing
• n best CCG Parsing
• Dominick Ng and James R
• Curran
• Using Smaller Constituents Rather Than Sentences
• Active Learning
• Japanese Dependency Parsing
• Exploiting Web Derived Selectional Preference
• Improve Statistical Dependency Parsing
• Guangyou Zhou
• Improving Arabic Dependency Parsing
• Form based
• Functional Morphological Features
• Tree Based Deterministic Dependency Parsing
• Kotaro Kitagawa Kumiko Tanaka Ishii
• Long Papers
• Event Extraction
• David McClosky
• Mihai Surdeanu
• Temporal Restricted
• Boltzmann Machines
• Transition based Dependency Parsing
• Rich Non local Features
• Yue Zhang
• Joint Training of Dependency Parsing Filters
• Latent Support Vector Machines
• Colin Cherry
• Getting the Most out
• Jinho D
• Choi
• Improving Dependency Parsing
• Semantic Classes
• Eneko Agirre
• An Ensemble Model
• Combines Syntactic and Semantic Clustering
• Discriminative Dependency Parsing
• Effects of Noun Phrase Bracketing
• Machine Translation
• Dependency Parsing and Projection
• Word Pair Classification
• Wenbin Jiang and Qun Liu Key
• Bitext Dependency Parsing
• Bilingual Subtree Constraints
• Cross Language Dependency Parsing
• Bilingual Lexicon∗
• xử lý ngôn ngữ tự nhiên
• Concise Integer Linear Programming Formulations
• F
• T
• Martins
• Non Projective Dependency Parsing
• Expected Linear Time
• Joakim Nivre Uppsala
• Cross Domain Dependency Parsing
• Deep Linguistic Grammar