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 present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features. Using these ideas together, the resulting tagger gives a 97.24% accuracy on the Penn Treebank WSJ, an error reduction of 4.4% on the best previous single automatically learned tagging result.

A comparison of algorithms for maximum entropy parameter estimation Conditional maximum entropy (ME) models provide a general purpose machine learning technique which has been successfully applied to fields as diverse as computer vision and econometrics, and which is used for a wide variety of classification problems in natural language processing. However, the flexibility of ME models is not without cost. While parameter estimation for ME models is conceptually straightforward, in practice ME models for typical natural language tasks are very large, and may well contain many thousands of free parameters. In this paper, we consider a number of algorithms for estimating the parameters of ME models, including iterative scaling, gradient ascent, conjugate gradient, and variable metric methods. Surprisingly, the standardly used iterative scaling algorithms perform quite poorly in comparison to the others, and for all of the test problems, a limited-memory variable metric algorithm outperformed the other choices.

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 sized representations of parse trees, such as the "all subtrees" (DOP) representation described by (Bod 98), or a representation tracking all sub-fragments of a tagged sentence. We give experimental results showing significant improvements on two tasks: parsing Wall Street Journal text, and named-entity extraction from web data.

This paper presents a novel discriminative learning technique for label sequences based on a combination of the two most successful learning algorithms, Support Vector Machines and Hidden Markov Models which we call Hidden Markov Support Vector Machine.

We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to the standard dynamic programs for parsing. In particular, it allows one to efficiently learn a model which discriminates among the entire space of parse trees, as opposed to reranking the top few candidates. Our models can condition on arbitrary features of input sentences, thus incorporating an important kind of lexical information without the added algorithmic complexity of modeling headedness. We provide an efficient algorithm for learning such models and show experimental evidence of the model’s improved performance over a natural baseline model and a lexicalized probabilistic context-free grammar. 1

This paper describes an incremental parsing approach where parameters are estimated using a variant of the perceptron algorithm. A beam-search algorithm is used during both training and decoding phases of the method. The perceptron approach was implemented with the same feature set as that of an existing generative model (Roark, 2001a), and experimental results show that it gives competitive performance to the generative model on parsing the Penn treebank. We demonstrate that training a perceptron model to combine with the generative model during search provides a 2.1 percent F-measure improvement over the generative model alone, to 88.8 percent. 1

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.

Conditional random fields (Lafferty et al., 2001) are quite effective at sequence labeling tasks like shallow parsing (Sha and Pereira, 2003) and namedentity extraction (McCallum and Li, 2003). CRFs are log-linear, allowing the incorporation of arbitrary features into the model. To train on unlabeled data, we require unsupervised estimation methods for log-linear models; few exist. We describe a novel approach, contrastive estimation. We show that the new technique can be intuitively understood as exploiting implicit negative evidence and is computationally efficient. Applied to a sequence labeling problem—POS tagging given a tagging dictionary and unlabeled text—contrastive estimation outperforms EM (with the same feature set), is more robust to degradations of the dictionary, and can largely recover by modeling additional features. 1

This paper describes a number of log-linear parsing models for an automatically extracted lexicalized grammar. The models are "full" parsing models in the sense that probabilities are defined for complete parses, rather than for independent events derived by decomposing the parse tree. Discriminative training is used to estimate the models, which requires incorrect parses for each sentence in the training data as well as the correct parse. The lexicalized grammar formalism used is Combinatory Categorial Grammar (CCG), and the grammar is automatically extracted from CCGbank, a CCG version of the Penn Treebank. The combination of discriminative training and an automatically extracted grammar leads to a significant memory requirement (over 20 GB), which is satisfied using a parallel implementation of the BFGS optimisation algorithm running on a Beowulf cluster. Dynamic programming over a packed chart, in combination with the parallel implementation, allows us to solve one of the largest-scale estimation problems in the statistical parsing literature in under three hours. A key component of the parsing system, for both training and testing, is a Maximum Entropy supertagger which assigns CCG lexical categories to words in a sentence. The supertagger makes the discriminative training feasible, and also leads to a highly efficient parser. Surprisingly,