tailieunhanh - Báo cáo khoa học: "Learning Accurate, Compact, and Interpretable Tree Annotation"

We present an automatic approach to tree annotation in which basic nonterminal symbols are alternately split and merged to maximize the likelihood of a training treebank. Starting with a simple Xbar grammar, we learn a new grammar whose nonterminals are subsymbols of the original nonterminals. | Learning Accurate Compact and Interpretable Tree Annotation Slav Petrov Leon Barrett Romain Thibaux Dan Klein Computer Science Division EECS Department University of California at Berkeley Berkeley CA 94720 petrov lbarrett thibaux klein @ Abstract We present an automatic approach to tree annotation in which basic nonterminal symbols are alternately split and merged to maximize the likelihood of a training treebank. Starting with a simple X-bar grammar we learn a new grammar whose nonterminals are subsymbols of the original nonterminals. In contrast with previous work we are able to split various terminals to different degrees as appropriate to the actual complexity in the data. Our grammars automatically learn the kinds of linguistic distinctions exhibited in previous work on manual tree annotation. On the other hand our grammars are much more compact and substantially more accurate than previous work on automatic annotation. Despite its simplicity our best grammar achieves an Fl of on the Penn Treebank higher than fully lexicalized systems. 1 Introduction Probabilistic context-free grammars PCFGs underlie most high-performance parsers in one way or another Collins 1999 Charniak 2000 Charniak and Johnson 2005 . However as demonstrated in Charniak 1996 and Klein and Manning 2003 a PCFG which simply takes the empirical rules and probabilities off of a treebank does not perform well. This naive grammar is a poor one because its context-freedom assumptions are too strong in some places . it assumes that subject and object NPs share the same distribution and too weak in others . it assumes that long rewrites are not decomposable into smaller steps . Therefore a variety of techniques have been developed to both enrich and generalize the naive grammar ranging from simple tree annotation and symbol splitting Johnson 1998 Klein and Manning 2003 to full lexicalization and intricate smoothing Collins 1999 Charniak 2000 . In this paper we .

• Báo cáo khoa học
• Learning Accurate
• Compact
• Interpretable Tree Annotation
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Accurate Learning
• Chinese Function Tags
• Minimal Features
• báo cáo ngôn ngữ
• Genome Biology
• Single cell
• Deep learning
• Semi supervised learning
• Downstream analysis
• Artificial neural network
• Machine learning
• Single cell genomics
• DNA methylation
• BMC Bioinformatics
• Protein protein interaction
• Biological processes
• Accurate high throughput methods
• BMC Genomics
• Taxonomic classification
• Whole genome analysis
• Genomic signature
• Alignment free sequence analysis
• Numerical representation of DNA sequences
• Digital signal processing
• Discrete Fourier transform
• RNA seq
• Neural network
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• Structural variations
• Feature extraction
• Genetic variations
• High throughput sequencing
• Tri disulfide peptide toxins
• Sequential tri disulfide peptides
• Nonknotted STPs
• Insecticidal peptides
• MiRNA disease association
• Similarity kernel
• Fast kernel learning
• Sparse kernel
• Laplacian regularized least squares
• Human diseases
• Variant calling
• Long range haplotype
• Difficult to map regions
• BMC Cancer
• Accurate prognosis assessment
• Intrahepatic cholangiocarcinoma
• Gradient boosting machine
• Non coding variants
• Disease specific
• Variant annotation
• Histone marks
• Feature selection
• Ensemble learning
• DNA N4 methylcytosine
• Sequence feature
• Site prediction
• DNA sequences
• Transcription factors
• DNase seq
• Cell type specific