Many Internet information-management applications (e.g., information integration systems) require a library of wrappers, specialized information extraction procedures that translate a source's native format into a structured representation suitable for further application-specific processing. Maintaining wrappers is tedious and error-prone, because the formatting regularities on which wrappers rely change frequently on the decentralized and dynamic Internet. The wrapper verification problem is to determine whether a wrapper is operating correctly. Standard regression testing approaches are inappropriate, because both the formatting regularities on which wrappers rely, and the source's underlying content, may change. We introduce rapture, a fully-implemented, domain-independent wrapper verification algorithm. rapture computes a probabilistic similarity measure between a wrapper's expected and observed output, where similarity is defined in terms of simple numeric features (e.g., the len...

We introduce a number of techniques designed to help integrate semantic knowledge with N-gram language models for automatic speech recognition. Our techniques allow us to integrate Latent Semantic Analysis (LSA), a word-similarity algorithm based on word co-occurrence information, with N-gram models. While LSA is good at predicting content words which are coherent with the rest of a text, it is a bad predictor of frequent words, has a low dynamic range, and is inaccurate when combined linearly with N-grams. We show that modifying the dynamic range, applying a per-word confidence metric, and using geometric rather than linear combinations with N-grams produces a more robust language model which has a lower perplexity on a Wall Street Journal testset than a baseline N-gram model. 1. INTRODUCTION There has been a lot of recent work on augmenting n-gram language models with other information sources such as longer distance syntactic, and semantic constraints (e.g. [8], [6]). In previous ...

In this paper, we propose a novel statistical language model to capture topic-related long-range dependencies. Topics are modeled in a latent variable framework in which we also derive an EM algorithm to perform a topic factor decomposition based on a segmented training corpus. The topic model is combined with a standard language model to be used for on-line word prediction. Perplexity results indicate an improvement over previously proposed topic models, which unfortunately has not translated into lower word error.

Speech recognition performance is severely affected when the lexical, syntactic, or semantic characteristics of the discourse in the training and recognition tasks differ. The aim of language model adaptation is to exploit specific, albeit limited, knowledge about the recognition task to compensate for this mismatch. More generally, an adaptive language model seeks to maintain an adequate representation of the current task domain under changing conditions involving potential variations in vocabulary, syntax, content, and style. This paper presents an overview of the major approaches proposed to address this issue, and offers some perspectives regarding their comparative merits and associated tradeoffs. Ó 2003 Elsevier B.V. All rights reserved. 1.

The study of phonotactics (e.g., the ability of English speakers to distinguish possible words like blick from impossible words like *bnick) is a central topic in phonology. We propose a theory of phonotactic grammars and a learning algorithm that constructs such grammars from positive evidence. Our grammars consist of constraints that are assigned numerical weights according to the principle of maximum entropy. Possible words are assessed by these grammars based on the weighted sum of their constraint violations. The learning algorithm yields grammars that can capture both categorical and gradient phonotactic patterns. The algorithm is not provided with any constraints in advance, but uses its own resources to form constraints and weight them. A baseline model, in which Universal Grammar is reduced to a feature set and an SPE-style constraint format, suffices to learn many phonotactic phenomena. In order to learn nonlocal phenomena such as stress and vowel harmony, it is necessary to augment the model with autosegmental tiers and metrical grids. Our results thus offer novel, learning-theoretic support for such representations. We apply the model to English syllable onsets, Shona vowel harmony, quantity-insensitive stress typology, and the full phonotactics of Wargamay, showing that the learned grammars capture the distributional generalizations of these languages and accurately predict the findings of a phonotactic experiment.

The eventual goal of a language model is to accurately predict the value of a missing word given its context. We present an approach to word prediction that is based on learning a representation for each word as a function of words and linguistics predicates in its context. This approach raises a few new questions that we address. First, in order to learn good word representations it is necessary to use an expressive representation of the context. We present a way that uses external knowledge to generate expressive context representations, along with a learning method capable of handling the large number of features generated this way that can, potentially, contribute to each prediction. Second, since the number of words "competing" for each prediction is large, there is a need to "focus the attention" on a smaller subset of these. We exhibit the contribution of a "focus of attention" mechanism to the performance of the word predictor. Finally, we describe a large scale experimental study in which the approach presented is shown to yield significant improvements in word prediction tasks.

We describe a new approach for statistical modeling and detection of discourse structure for natural conversational speech. Our model is based on 42 `Dialog Acts' (DAs), (question, answer, backchannel, agreement, disagreement, apology, etc). We labeled 1155 conversations from the Switchboard (SWBD) database (Godfrey et al. 1992) of human-to-human telephone conversations with these 42 types and trained a Dialog Act detector based on three distinct knowledge sources: sequences of words which characterize a dialog act, prosodic features which characterize a dialog act, and a statistical Discourse Grammar. Our combined detector, although still in preliminary stages, already achieves a 65% Dialog Act detection rate based on acoustic waveforms, and 72% accuracy based on word transcripts. Using this detector to switch among the 42 dialog-act-specific trigram LMs also gave us an encouraging but not statistically significant reduction in SWBD word error. 1 Introduction The ability to model and...

Abstract. This paper addresses two central problems for probabilistic processing models: parameter estimation from incomplete data and efficient retrieval of most probable analyses. These questions have been answered satisfactorily only for probabilistic regular and context-free models. We address these problems for a more expressive probabilistic constraint logic programming model. We present a log-linear probability model for probabilistic constraint logic programming. On top of this model we define an algorithm to estimate the parameters and to select the properties of log-linear models from incomplete data. This algorithm is an extension of the improved iterative scaling algorithm of Della Pietra, Della Pietra, and Lafferty (1995). Our algorithm applies to loglinear models in general and is accompanied with suitable approximation methods when applied to large data spaces. Furthermore, we present an approach for searching for most probable analyses of the probabilistic constraint logic programming model. This method can be applied to the ambiguity resolution problem in natural language processing applications. 1.

This paper describes maxent in detail and presents an Increment Feature Selection algorithm for increasingly construct a maxent model as well as several example in statistical Machine Translation

We describe an integrated approach for statistical modeling of discourse structure for natural conversational speech. Our model is based on 42 `dialog acts' (e.g., Statement, Question, Backchannel, Agreement, Disagreement, Apology), which were hand-labeled in 1155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We developed several models and algorithms to automatically detect dialog acts from transcribed or automatically recognized words and from prosodic properties of the speech signal, and by using a statistical discourse grammar. All of these components were probabilistic in nature and estimated from data, employing a variety of techniques (hidden Markov models, N-gram language models, maximum entropy estimation, decision tree classifiers, and neural networks). In preliminary studies, we achieved a dialog act labeling accuracy of 65% based on recognized words and prosody, and an accuracy of 72% based on word transcripts. Since humans achiev...