This article describes three statistical models for natural language parsing. The models extend methods from probabilistic context-free grammars to lexicalized grammars, 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. Independence assumptions then lead to parameters that encode the X-bar schema, subcategorization, ordering of complements, placement of adjuncts, bigram lexical dependencies, wh-movement, and preferences for close attachment. All of these preferences are expressed by probabilities conditioned on lexical heads. The models are evaluated on the Penn Wall Street Journal Treebank, showing that their accuracy is competitive with other models in the literature. To gain a better understanding of the models, we also give results on different constituent types, as well as a breakdown of precision/recall results in recovering various types of dependencies. We analyze various characteristics of the models through experiments on parsing accuracy, by collecting frequencies of various structures in the treebank, and through linguistically motivated examples. Finally, we compare the models to others that have been applied to parsing the treebank, aiming to give some explanation of the difference in performance of the various models

Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the development of standard evaluation datasets and extensive comparison among methods. We show here how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model. Improved training methods based on modern optimization algorithms were critical in achieving these results. We present extensive comparisons between models and training methods that confirm and strengthen previous results on shallow parsing and training methods for maximum-entropy models.

The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent coreference, quantification, and many other higher-order phenomena, but also broad, in that it covers every instance of every verb in the corpus and allows representative statistics to be calculated. We discuss the criteria used to define the sets of semantic roles used in the annotation process and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty ‘‘trace’ ’ categories of the treebank.

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 these features interact or overlap and without the need to define a derivation or a generative model which takes these features into account. We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). We apply the boosting method to parsing the Wall Street Journal treebank. The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model. The new model achieved 89.75 % F-measure, a 13 % relative decrease in F-measure error over the baseline model’s score of 88.2%. The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in the parsing data. Experiments show significant efficiency gains for the new algorithm over the obvious implementation of the boosting approach. We argue that the method is an appealing alternative—in terms of both simplicity and efficiency—to work on feature selection methods within log-linear (maximum-entropy) models. Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation.

We discuss the relevance of k-best parsing to recent applications in natural language processing, and develop efficient algorithms for k-best trees in the framework of hypergraph parsing. To demonstrate the efficiency, scalability and accuracy of these algorithms, we present experiments on Bikel’s implementation of Collins ’ lexicalized PCFG model, and on Chiang’s CFG-based decoder for hierarchical phrase-based translation. We show in particular how the improved output of our algorithms has the potential to improve results from parse reranking systems and other applications. 1

We show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural language processing tasks: grapheme-to-phoneme conversion, part-of-speech tagging, prepositional-phrase attachment, and base noun phrase chunking. In a first series of experiments we combine memory-based learning with training set editing techniques, in which instances are edited based on their typicality and class prediction strength. Results show that editing exceptional instances (with low typicality or low class prediction strength) tends to harm generalization accuracy. In a second series of experiments we compare memory-based learning and decision-tree learning methods on the same selection of tasks, and find that decision-tree learning often performs worse than memory-based learning. Moreover, the decrease in performance can be linked to the degree of abstraction from exceptions (i.e., pruning or eagerness). We provide explanations for both results in terms of the properties of the natural language processing tasks and the learning algorithms.

This paper describes a novel statistical namedentity (i.e. "proper name") recognition system built around a maximum enti W framework. By working within the framework of maximum entropy. theory and utilizing a flexible object-based architecture, the system is able to make use of an extraordinarily diverse range of knowledge sources in making its tagging decisions. These knowledge sources include capitalization features, lexical features, features in- dicating the current section of text (i.e. headline or main body), and dictionaries of single or multi-wtrd terms. The purely statistical system contains no hand-generated patterns and achieves a result comparable with the best statistical systems. However, when combined with other handcoded systems, the system achieves scores that exceed the highest comparable scores thus-far published.

The recent growth of online information available in the form of natural language documents creates a greater need for computing systems with the ability to process those documents to simplify access to the information. One type of processing appropriate for many tasks is information extraction, a type of text skimming that retrieves specific types of information from text. Although information extraction systems have existed for two decades, these systems have generally been built by hand and contain domain specific information, making them difficult to port to other domains. A few researchers have begun to apply machine learning to information extraction tasks, but most of this work has involved applying learning to pieces of a much larger system. This paper presents a novel rule representation specific to natural language and a learning system, Rapier, which learns information extraction rules. Rapier takes pairs of documents and filled templates indicating the information to be ext...

Most work in statistical parsing has focused on a single corpus: the Wall Street Journal portion of the Penn Treebank. While this has allowed for quantitative comparison of parsing techniques, it has left open the question of how other types of text might a#ect parser performance, and how portable parsing models are across corpora. We examine these questions by comparing results for the Brown and WSJ corpora, and also consider which parts of the parser's probability model are particularly tuned to the corpus on which it was trained. This leads us to a technique for pruning parameters to reduce the size of the parsing model. 1

Probabilistic Context-Free Grammars (PCFGs) and variations on them have recently become some of the most common formalisms for parsing. It is common with PCFGs to compute the inside and outside probabilities. When these probabilities are multiplied together and normalized, they produce the probability that any given non-terminal covers any piece of the input sentence. The traditional use of these probabilities is to improve the probabilities of grammar rules. In this thesis we show that these values are useful for solving many other problems in Statistical Natural Language Processing. We give a framework for describing parsers. The framework generalizes the inside and outside values to semirings. It makes it easy to describe parsers that compute a wide variety of interesting quantities, including the inside and outside probabilities, as well as related quantities such as Viterbi probabilities and n-best lists. We also present three novel uses for the inside and outside probabilities. T...