TAILIEUCHUNG - Báo cáo khoa học: "Efficient, Feature-based, Conditional Random Field Parsing"

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data. | Efficient Feature-based Conditional Random Field Parsing Jenny Rose Finkel Alex Kleeman Christopher D. Manning Department of Computer Science Stanford University Stanford CA 94305 jrfinkel@ akleeman@ manning@ Abstract Discriminative feature-based methods are widely used in natural language processing but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences we present the first general featurerich discriminative parser based on a conditional random field model which has been successfully scaled to the full WSJ parsing data. Our efficiency is primarily due to the use of stochastic optimization techniques as well as parallelization and chart prefiltering. On WSJ15 we attain a state-of-the-art F-score of a 14 relative reduction in error over previous models while being two orders of magnitude faster. On sentences of length 40 our system achieves an F-score of a 36 relative reduction in error over a generative baseline. 1 Introduction Over the past decade feature-based discriminative models have become the tool of choice for many natural language processing tasks. Although they take much longer to train than generative models they typically produce higher performing systems in large part due to the ability to incorporate arbitrary potentially overlapping features. However constituency parsing remains an area dominated by generative methods due to the computational complexity of the problem. Previous work on discriminative parsing falls under one of three approaches. One approach does discriminative reranking of the 7-best list of a generative parser still usually depending highly on the generative parser score as a feature Collins 2000 Charniak and Johnson 2005 . A second group of papers does parsing by a sequence of independent discriminative decisions either greedily or with use of a .

• Báo cáo khoa học
• Efficient
• Feature based
• Conditional Random Field Parsing
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Random Oracle model
• A Paradigm for Designing Efficient Protocols
• Designing Efficient Protocols
• Random oracle paradigm
• Chosen Cipher text Security
• A digital signature scheme
• Exploring Deterministic Constraints
• Constrained English POS Tagger
• Efficient ILP Solution
• Chinese Word Segmentation
• ngôn ngữ tự nhiên
• Efficient Tree Based Topic Modeling
• Yuening Hu
• Long Papers
• Efficient Tree based Approximation
• Entailment Graph Learning
• Jonathan Berant
• Efficient Search
• Transformation based Inference
• Efficient Staggered Decoding
• Sequence Labeling
• Nobuhiro Kaji Yasuhiro Fujiwara Naoki Yoshinaga Masaru Kitsuregawa
• Efficient Inference Through Cascades
• Weighted Tree Transducers
• Jonathan May and Kevin Knight
• Efficient Path Counting Transducers
• Minimum Bayes Risk Decoding
• Statistical Machine Translation Lattices
• Efficient CCG Parsing
• A versus Adaptive Supertagging
• Efficient Online Locality
• Sensitive Hashing
• Reservoir Counting
• Unary Constraints
• Efficient Context Free Parsing
• Nathan Bodenstab
• Efficient Third order Dependency Parsers
• Terry Koo and Michael Collins
• Efficient Minimum Error Rate Training
• Translation Hypergraphs and Lattices
• Semi Supervised SimHash
• Efficient Document Similarity Search
• Qixia Jiang and Maosong Sun
• Beam Width Prediction
• Efficient Inference of CRFs
• Large Scale Natural Language Data
• Minwoo Jeong
• Efficient Multi pass Decoding
• Synchronous Context Free Grammars
• Hao Zhang and Daniel Gildea
• Mixture Model POMDPs
• Efficient Handling of Uncertainty
• Dialogue Management
• Efficient Unsupervised Discovery of Word Categories
• Symmetric Patterns
• High Frequency Words
• mô hình ngôn ngữ
• Space Efficient
• non Heuristic
• Polynomial Kernel Computation
• NLP Applications
• Efficient Processing
• Underspecified Discourse Representations
• Michaela Regneri
• Computationally Efficient M Estimation
• Log Linear Structure Models
• Noah A
• Smith and Douglas L
• Vail and John D
• Lafferty
• Efficient sentence retrieval
• syntactic structure
• Ichikawa Hiroshi
• An efficient algorithm
• building a distributional thesaurus
• Sketch Engine developments