Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking
Eugene Charniak,Mark Johnson +1 more
- pp 173-180
TLDR
This paper describes a simple yet novel method for constructing sets of 50- best parses based on a coarse-to-fine generative parser that generates 50-best lists that are of substantially higher quality than previously obtainable.Abstract:
Discriminative reranking is one method for constructing high-performance statistical parsers (Collins, 2000). A discriminative reranker requires a source of candidate parses for each sentence. This paper describes a simple yet novel method for constructing sets of 50-best parses based on a coarse-to-fine generative parser (Charniak, 2000). This method generates 50-best lists that are of substantially higher quality than previously obtainable. We used these parses as the input to a MaxEnt reranker (Johnson et al., 1999; Riezler et al., 2002) that selects the best parse from the set of parses for each sentence, obtaining an f-score of 91.0% on sentences of length 100 or less.read more
Citations
More filters
Proceedings ArticleDOI
ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
TL;DR: The ChestX-ray dataset as discussed by the authors contains 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight disease image labels from the associated radiological reports using natural language processing.
Proceedings Article
Recurrent convolutional neural networks for text classification
TL;DR: A recurrent convolutional neural network is introduced for text classification without human-designed features to capture contextual information as far as possible when learning word representations, which may introduce considerably less noise compared to traditional window-based neural networks.
Proceedings ArticleDOI
ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
TL;DR: A new chest X-rays database, namely ChestX-ray8, is presented, which comprises 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight disease image labels from the associated radiological reports using natural language processing, which is validated using the proposed dataset.
Journal ArticleDOI
CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison
Jeremy Irvin,Pranav Rajpurkar,Michael Ko,Yifan Yu,Silviana Ciurea-Ilcus,Christopher G. Chute,Henrik Marklund,Behzad Haghgoo,Robyn L. Ball,Katie Shpanskaya,Jayne Seekins,David A. Mong,Safwan Halabi,Jesse K. Sandberg,Ricky Jones,David B. Larson,Curtis P. Langlotz,Bhavik N. Patel,Matthew P. Lungren,Andrew Y. Ng +19 more
TL;DR: CheXpert as discussed by the authors is a large dataset of chest radiographs of 65,240 patients annotated by 3 board-certified radiologists with 14 observations in radiology reports, capturing uncertainties inherent in radiograph interpretation.
Proceedings ArticleDOI
Learning Accurate, Compact, and Interpretable Tree Annotation
TL;DR: An automatic approach to tree annotation in which basic nonterminal symbols are alternately split and merged to maximize the likelihood of a training treebank is presented.
References
More filters
Proceedings ArticleDOI
Accurate Unlexicalized Parsing
Dan Klein,Christopher D. Manning +1 more
TL;DR: It is demonstrated that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar.
Proceedings Article
A maximum-entropy-inspired parser
TL;DR: A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
Proceedings ArticleDOI
Three Generative, Lexicalised Models for Statistical Parsing
TL;DR: The authors proposed a new statistical parsing model, which is a generative model of lexicalised context-free grammar, and extended the model to include a probabilistic treatment of both subcategorisation and wh-movement.
Posted Content
Three Generative, Lexicalised Models for Statistical Parsing
TL;DR: A new statistical parsing model is proposed, which is a generative model of lexicalised context-free grammar and extended to include a probabilistic treatment of both subcategorisation and wh-movement.
Proceedings ArticleDOI
A comparison of algorithms for maximum entropy parameter estimation
TL;DR: A number of algorithms for estimating the parameters of ME models are considered, including iterative scaling, gradient ascent, conjugate gradient, and variable metric methods.