Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques

By Stefan Riezler, Tracy Holloway King, Ronald M. Kaplan, Dick Crouch, John T. Maxwell, Mark Johnson. Annual Meeting of the Association for Computational Linguistics, 2002

339 citations recorded by the source corpus.

We present a stochastic parsing system consisting of a Lexical-Functional Grammar (LFG), a constraint-based parser and a stochastic disambiguation model. We report on the results of applying this system to parsing the UPenn Wall Street Journal (WSJ) treebank. The model combines full and partial parsing techniques to reach full grammar coverage on unseen data. The treebank annotations are used to provide partially labeled data for discriminative statistical estimation using exponential models. Disambiguation performance is evaluated by measuring matches of predicate-argument relations on two distinct test sets. On a gold standard of manually annotated f-structures for a subset of the WSJ treebank, this evaluation reaches 79% F-score. An evaluation on a gold standard of dependency relations for Brown corpus data achieves 76% F-score.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/7f8f8f33187e20768ae0177780ac5ef78b77feca

How researchers see this paper

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

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Constituent Parsing with Incremental Sigmoid Belief Networks (2007, background): “There has not been much previous work on graphical models for full parsing, although recently several latent variable models for parsing have been proposed (Koo and Collins, 2005; Matsuzaki et al., 2005; Riezler et al., 2002).”
Parsing the WSJ Using CCG and Log-Linear Models (2004, methodology): “Log-linear models have been applied to the parsing problem across a range of grammar formalisms, e.g. Riezler et al. (2002) and Toutanova et al. (2002).”
TIGER: Linguistic Interpretation of a German Corpus (2004, methodology): “Furthermore, to minimize manual effort, a statistical disambiguation tool can be integrated ( Riezler et al., 2002 ).”
Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing (2015, neutral): “, Sarkar (2000); Hockenmaier & Steedman (2002); Riezler et al. (2002); Clark & Curran (2007); Miyao & Tsujii (2005)).”
Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking (2005, background): “Recall the standard MaxEnt conditional probability model for a parse y ∈ Y : , where The loss function L D proposed in Riezler et al. (2002) is just the negative log conditional likelihood of the best parses Y + ( s ) relative to the n -best parser output Y ( s ) : , where The partial derivatives…”
A Latent Variable Model for Generative Dependency Parsing (2007, background): “Recently several latent variable models for constituent parsing have been proposed (Koo and Collins, 2005; Matsuzaki et al., 2005; Prescher, 2005; Riezler et al., 2002).”
An Introduction to Conditional Random Fields (2010, methodology): “Also, there is work on using CRFs to learn distributions over the derivations of a grammar [99, 19, 127, 31].”
Entailment, intensionality and text understanding (2003, background): “Evaluation of essentially the same grammar on a dependency annotated subset of section 23 of the UPenn Wall Street Journal gives the accuracy of best parses as 85%, increasing by another 4% for nonfragmentary analyses (Riezler et al., 2002).”
Incremental Parsing with the Perceptron Algorithm (2004, methodology): “For example, Johnson et al. (1999) and Riezler et al. (2002) use all parses generated by an LFG parser as input to an MRF approach – given the level of ambiguity in natural language, this set can presumably become extremely large.”
Analysis by Synthesis: A (Re-)Emerging Program of Research for Language and Vision (2010, methodology): “For example, Morgan et al. (2010) propose a statistical interpretation of the set of categorial grammatical rules that generate the benchmark trees in the Penn Tree Bank; Riezler et al. (2002) make a similar proposal for interpreting Lexical Functional Grammatical Rules.”
Further Meta-Evaluation of Broad-Coverage Surface Realization (2010, methodology): “The LFG f-structures used as input to the XLE generator were derived from automatic parses, as described in (Riezler et al., 2002).”
An Introduction to Conditional Random Fields for Relational Learning (2007, neutral): “Also, there is work on using CRFs to learn distributions over the derivations of a grammar [Riezler et al., 2002, Clark and Curran, 2004, Sutton, 2004, Viola and Narasimhan, 2005].”
Shallow Parsing with Conditional Random Fields (2003, background): “However, work in that direction has so far addressed only parse reranking (Collins and Duffy, 2002; Riezler et al., 2002).”
Parser Evaluation over Local and Non-Local Deep Dependencies in a Large Corpus (2011, methodology): “XLE/ParGram (Riezler et al., 2002, see also Cahill et al., 2008) applies a hand-built Lexical Functional Grammar for English and a stochastic parse selection model.”
Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models (2007, methodology): “We follow Riezler et al. (2002) in using a discriminative estimation method by maximizing the conditional log-likelihood of the model given the data, minus a Gaussian prior 2 We could model predicate–argument dependencies together with the derivation, but we wanted to use features from the…”
Learning Syntax from Naturally-Occurring Bracketings (2021, background): “…learning for dependency parsing (Sassano, 2005; Sassano and Kurohashi, 2010; Mirroshandel and Nasr, 2011; Flannery et al., 2011; Flannery and Mori, 2015; Li et al., 2016; Zhang et al., 2017) and grammar induction for constituency parsing (Pereira and Schabes, 1992; Hwa, 1999; Riezler et al., 2002).”
Discriminative Reranking for Natural Language Parsing (2000, methodology): “…of boosting methods to ranking problems in Freund et al. (1998); we also introduce an approach related to the conditional log-linear models of Ratnaparkhi, Roukos, and Ward (1994), Papineni, Roukos, and Ward (1997, 1998), Johnson et al. (1999), Riezler et al. (2002), and Och and Ney (2002).”
Online Large-Margin Training of Dependency Parsers (2005, background): “Discriminatively trained parsers that score entire trees for a given sentence have only recently been investigated (Riezler et al., 2002; Clark and Curran, 2004; Collins and Roark, 2004; Taskar et al., 2004).”