We analyze a few of the commonly used statistics based and machine learning algorithms for natural language disambiguation tasks and observe that they can be recast as learning linear separators in the feature space. Each of the methods makes a priori assumptions, which it employs, given the data, when searching for its hypothesis. Nevertheless, as we show, it searches a space that is as rich as the space of all linear separators. We use this to build an argument for a data driven approach which merely searches for a good linear separator in the feature space, without further assumptions on the domain or a specific problem. We present such an approach - a sparse network of linear separators, utilizing the Winnow learning algorithm - and show how to use it in a variety of ambiguity resolution problems. The learning approach presented is attribute-efficient and, therefore, appropriate for domains having very large number of attributes. In particular, we present an extensive experimental ...

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or incrementally learned feature space and is specifically tailored for learning in the presence of a very large number of features. A wide range of face images in different poses, with different expressions and under different lighting conditions are used as a training set to capture the variations of human faces. Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and others. Furthermore, learning and evaluation using the SNoW-based method are significantly more efficient than with other methods.

A SNoW based learning approach to shallow parsing tasks is presented and studied experimentally. The approach learns to identify syntactic patterns by combining simple predictors to produce a coherent inference. Two instantiations of this approach are studied and experimental results for Noun-Phrases (NP) and Subject-Verb (SV) phrases that compare favorably with the best published results are presented. In doing that, we compare two ways of modeling the problem of learning to recognize patterns and suggest that shallow parsing patterns are bet- ter learned using open/close predictors than using inside/outside predictors.

We introduce constraint classification, a framework capturing many flavors of multiclass classification including multilabel classification and ranking, and present a meta-algorithm for learning in this framework. We provide generalization bounds when using a collection of k linear functions to represent each hypothesis. We also present empirical and theoretical evidence that constraint classification is more powerful than existing methods of multiclass classification. 1

This paper describes an extension to the hidden Markov model for part-of-speech tagging using second-order approximations for both contex-tual and lexical probabilities. This model in-creases the accuracy of the tagger to state of the art levels. These approximations make use of more contextual information than standard statistical systems. New methods of smoothing the estimated probabilities are also introduced to address the sparse data problem. 1

Statistics-based classifiers in natural language are developed typically by assuming a generative model for the data, estimating its parameters from training data and then using Bayes rule to obtain a classifier. For many problems the assumptions made by the generative models are evidently wrong, leaving open the question of why these approaches work. This paper presents a learning theory account of the major statistical approaches to learning in natural language. A class of Linear Statistical Queries (LSQ) hypotheses is defined and learning with it is shown to exhibit some robustness properties. Many statistical learners used in natural language, including naive Bayes, Markov Models and Maximum Entropy models are shown to be LSQ hypotheses, explaining the robustness of these predictors even when the underlying probabilistic assumptions do not hold. This coherent view of when and why learning approaches work in this context may help to develop better learning methods and an understanding of the role of learning in natural language inferences. 1

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.

Many classification problems require decisions among a large number of competing classes. These tasks, however, are not handled well by general purpose learning methods and are usually addressed in an ad-hoc fashion. We suggest a general approach – a sequential learning model that utilizes classifiers to sequentially restrict the number of competing classes while maintaining, with high probability, the presence of the true outcome in the candidates set. Some theoretical and computational properties of the model are discussed and we argue that these are important in NLP-like domains. The advantages of the model are illustrated in an experiment in partof-speech tagging. 1

Software errors are a major cause for system failures. To effectively design tools and support for detecting and recovering from software failures requires a deep understanding of bug 1 characteristics. Recently, software and its development process have significantly changed in many ways, including more help from bug detection tools, shift towards multi-threading architecture, the opensource development paradigm and increasing concerns about security and user-friendly interface. Therefore, results from previous studies may not be applicable to present software. Furthermore, many new aspects such as security, concurrency and open-sourcerelated characteristics have not well studied. Additionally, previous studies were based on a small number of bugs, which may lead to non-representative results. To investigate the impacts of the new factors on software errors,

We describe a coherent view of learning and reasoning with relational representations in the context of natural language processing. In particular, we discuss the Neuroidal Architecture, Inductive Logic Programming and the SNoW system explaining the relationships among these, and thereby oer an explanation of the theoretical basis for the SNoW system. We suggest that extensions of this system along the lines suggested by the theory may provide new levels of scalability and functionality. 1 Introduction The paper explores some aspects of relational knowledge representation and their learnability. While the discussion is to a large extent general it is made in the context of low-level natural language processing (NLP) tasks. Recent eorts in NLP emphasize empirical approaches, that attempt to learn how to perform various natural language tasks by being trained using an annotated corpus. These approaches have been used for a wide variety of fairly low level tasks such as part-of-speech...