Forest Reranking: Discriminative Parsing with Non-Local Features

By Liang Huang. 2008

287 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017, methodology): “Re-ranking has been commonly used in NLP problems, such as in parsing and translation, in order to make use of high-order or global features that are too expensive for decoding algorithms (Collins & Koo, 2005; Shen et al., 2004; Huang, 2008; Dyer et al., 2016).”
A Simple, Fast Diverse Decoding Algorithm for Neural Generation (2016, methodology): “Diverse decoding has been sufficiently explored in phrase-based MT, where the output space is approximated by the N-best list (Huang, 2008; Finkel et al., 2006).”
Unbounded Dependency Recovery for Parser Evaluation (2009, background): “Statistical parsers are now obtaining Parseval scores of over 90% on the WSJ section of the Penn Treebank (Bod, 2003; Petrov and Klein, 2007; Huang, 2008; Carreras et al., 2008).”
Self-Training PCFG Grammars with Latent Annotations Across Languages (2009, methodology): “Better results would be expected by combining the PCFG-LA parser with discriminative reranking approaches (Charniak and Johnson, 2005; Huang, 2008) for self training.”
11,001 New Features for Statistical Machine Translation (2009, methodology): “First, it used the features for reranking n -best lists of translations, rather than for decoding or forest reranking (Huang, 2008).”
Unsupervised Concept-to-text Generation with Hypergraphs (2012, methodology): “In the future, we plan to remedy this by using forest reranking, a technique that approximately reranks a packed forest of exponentially many derivations (Huang, 2008).”
SpanNER: Named Entity Re-/Recognition as Span Prediction (2021, methodology): “, 2020) as well as its re-ranking (Collins and Koo, 2005; Huang, 2008) as a span prediction (Stern et al.”
Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing (2015, background): “3, and pruning edges according to a figure-of-merit (Huang, 2008b; Charniak & Johnson, 2005).”
First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests (2009, methodology): “To achieve competitive performance, we adopt a forest reranking approach (Li and Khudanpur, 2009; Huang, 2008).”
Mutual Information and Diverse Decoding Improve Neural Machine Translation (2016, background): “Unfortunately, the N-best lists outputted from standard beam search are a poor surrogate for the entire search space (Finkel et al., 2006; Huang, 2008).”
In-Order Transition-based Constituent Parsing (2017, unknown): “With the reranking setting, the in-order parser outperforms the best discrete parser (Huang, 2008) and have the same performance of Kuncoro et al. (2017), which extend the work of Dyer et al. (2016) by adding gated attention mechanism on composition functions.”
Feature Optimization for Constituent Parsing via Neural Networks (2015, background): “Lei et al. (2014) proposed to learn features by representing the cross-products of some primitive units with low-rank tensors for dependency parsing.”
The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization (2015, methodology): “For instance, the chart pruner proposed by Huang (2008) has a forest oracle of 97.”
Self-Training with Products of Latent Variable Grammars (2010, methodology): “McClosky et al. (2006) presented a very effective method for self-training a two-stage parsing system consisting of a first-stage generative lexicalized parser and a second-stage discriminative reranker.”
Hope and Fear for Discriminative Training of Statistical Translation Models (2012, background): “(2007), who use a special case of forest reranking (Huang, 2008).”
Dependency Parsing by Belief Propagation (2008, background): “We are interested in extending these ideas to phrase-structure and lattice parsing, and in trying other higher-order features, such as those used in parse reranking (Charniak and Johnson, 2005; Huang, 2008) and history-based parsing (Nivre and McDonald, 2008).”
Structured learning with constrained conditional models (2012, background): “Recently, Daumé and Marcu (2005), Kazama and Torisawa (2007), Huang (2008) proposed to use approximate inference procedure and let the weights of the long distance features guide the search procedure.”