Discriminative Reranking for Natural Language Parsing

@article{Collins2005DiscriminativeRF,
  title={Discriminative Reranking for Natural Language Parsing},
  author={Michael Collins and Terry Koo},
  journal={Computational Linguistics},
  year={2005},
  volume={31},
  pages={25-70}
}
This article considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. A second model then attempts to improve upon this initial ranking, using additional features of the tree as evidence. The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how… Expand
Hybrid Syntactic-Semantic Reranking for Parsing Results of ECAs Interactions Using CRFs
TLDR
A new discriminative reranking method of parsing results has been applied using Conditional Random Fields (CRFs) for sequence tagging and a mixture of syntactic and semantic features, specifically designed for Embodied Conversational Agents (ECAs) interactions, has been used. Expand
A Progress Report on Bitext Parsing
Recent work has shown that a reranking approach can be used to improve the syntactic parsing of a sentence given a translation of that sentence, an automatically generated parse of that translation,Expand
Hidden-Variable Models for Discriminative Reranking
TLDR
A conditional log-linear model is made use, with hidden variables representing the assignment of lexical items to word clusters or word senses, based on a discriminative training criterion for NLP structures within reranking approaches. Expand
Parse reranking with WordNet using a hidden variable model
TLDR
A new parse reranking algorithm is presented that extends work in (Michael Collins and Terry Koo 2004) by incorporating WordNet word senses and defines a probability distribution over candidate parses and word sense assignments with a feature-based log-linear model, and employs belief propagation to obtain an efficient implementation. Expand
Dependency Parse Reranking with Rich Subtree Features
TLDR
This work explores a new reranking approach for dependency parsing that can utilize complex subtree representations by applying efficient subtree selection methods and achieves the best performance among known supervised systems evaluated on these datasets. Expand
K-Best Combination of Syntactic Parsers
TLDR
A linear model-based general framework to combine k-best parse outputs from multiple parsers by integrating them into a linear model able to fully utilize both the logarithm of the probability of each k- best parse tree from each individual parser and any additional useful features. Expand
Corrective Dependency Parsing
TLDR
This chapter presents a discriminative modeling technique which corrects the errors made by an automatic parser, and shows that the only requirement for this technique is the ability to define a local neighborhood in which a large number of the errors occur. Expand
A reranking method for syntactic parsing with heterogeneous treebanks
  • Haibo Ding, Muhua Zhu, Jingbo Zhu
  • Computer Science
  • Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)
  • 2010
TLDR
This paper takes syntactic parsing as a case study and proposes a reranking method which is able to make direct use of disparate treebanks simultaneously without using techniques such as treebank conversion. Expand
Head-Driven Statistical Models for Natural Language Parsing
  • M. Collins
  • Computer Science
  • Computational Linguistics
  • 2003
TLDR
Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree. Expand
Improving Semantic Parsing with Neural Generator-Reranker Architecture
TLDR
A generator-reranker architecture for semantic parsing that consists of a pre-processing step for the candidates followed by a novel critic network, which reranks these candidates based on the similarity between each candidate and the input sentence. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 68 REFERENCES
Head-Driven Statistical Models for Natural Language Parsing
  • M. Collins
  • Computer Science
  • Computational Linguistics
  • 2003
TLDR
Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree. Expand
Towards History-based Grammars: Using Richer Models for Probabilistic Parsing
TLDR
HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way and significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. Expand
Using LTAG Based Features in Parse Reranking
TLDR
This paper extends the notion of a tree kernel over arbitrary sub-trees of the parse to the derivation trees and derived trees provided by the LTAG formalism, and in addition, it extends the original definition of the tree kernel, making it more lexicalized and more compact. Expand
Inducing History Representations for Broad Coverage Statistical Parsing
TLDR
A neural network method for inducing representations of parse histories and using these history representations to estimate the probabilities needed by a statistical left-corner parser achieves performance on the Penn Treebank which is only 0.6% below the best current parser for this task. Expand
A Maximum-Entropy-Inspired Parser
TLDR
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. Expand
Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques
TLDR
The model combines full and partial parsing techniques to reach full grammar coverage on unseen data, and on a gold standard of manually annotated f-structures for a subset of the WSJ treebank, reaches 79% F-score. Expand
Maximum entropy models for natural language ambiguity resolution
This thesis demonstrates that several important kinds of natural language ambiguities can be resolved to state-of-the-art accuracies using a single statistical modeling technique based on theExpand
New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron
This paper introduces new learning algorithms for natural language processing based on the perceptron algorithm. We show how the algorithms can be efficiently applied to exponential sizedExpand
SPoT: A Trainable Sentence Planner
TLDR
This paper presents SPoT, a sentence planner, and a new methodology for automatically trainingSPoT on the basis of feedback provided by human judges, and shows that the trained SPR learns to select a sentence plan whose rating on average is only 5% worse than the top human-ranked sentence plan. Expand
Statistical Parsing with a Context-Free Grammar and Word Statistics
TLDR
A parsing system based upon a language model for English that is, in turn, based upon assigning probabilities to possible parses for a sentence that outperforms previous schemes is described. Expand
...
1
2
3
4
5
...