Broad coverage, high quality parsers are available for only a handful of languages. A prerequisite for developing broad coverage parsers for more languages is the annotation of text with the desired linguistic representations (also known as “treebanking”). However, syntactic annotation is a labor intensive and time-consuming process, and it is difficult to find linguistically annotated text in sufficient quantities. In this article, we explore using parallel text to help solving the problem of creating syntactic annotation in more languages. The central idea is to annotate the English side of a parallel corpus, project the analysis to the second language, and then train a stochastic analyzer on the resulting noisy annotations. We discuss our background assumptions, describe an initial study on the “projectability ” of syntactic relations, and then present two experiments in which stochastic parsers are developed with minimal human intervention via projection from English. 1

We present a family of priors over probabilistic grammar weights, called the shared logistic normal distribution. This family extends the partitioned logistic normal distribution, enabling factored covariance between the probabilities of different derivation events in the probabilistic grammar, providing a new way to encode prior knowledge about an unknown grammar. We describe a variational EM algorithm for learning a probabilistic grammar based on this family of priors. We then experiment with unsupervised dependency grammar induction and show significant improvements using our model for both monolingual learning and bilingual learning with a non-parallel, multilingual corpus. 1

Statistical machine translation (SMT) treats the translation of natural language as a machine learning problem. By examining many samples of human-produced translation, SMT algorithms automatically learn how to translate. SMT has made tremendous strides in less than two decades, and many popular techniques have only emerged within the last few years. This survey presents a tutorial overview of state-of-the-art SMT at the beginning of 2007. We begin with the context of the current research, and then move to a formal problem description and an overview of the four main subproblems: translational equivalence modeling, mathematical modeling, parameter estimation, and decoding. Along the way, we present a taxonomy of some different approaches within these areas. We conclude with an overview of evaluation and notes on future directions.

We describe a novel training criterion for probabilistic grammar induction models, contrastive estimation [Smith and Eisner, 2005], which can be interpreted as exploiting implicit negative evidence and includes a wide class of likelihood-based objective functions. This criterion is a generalization of the function maximized by the Expectation-Maximization algorithm [Dempster et al., 1977]. CE is a natural fit for log-linear models, which can include arbitrary features but for which EM is computationally difficult. We show that, using the same features, log-linear dependency grammar models trained using CE can drastically outperform EMtrained generative models on the task of matching human linguistic annotations (the MATCHLIN-GUIST task). The selection of an implicit negative evidence class—a “neighborhood”—appropriate to a given task has strong implications, but a good neighborhood one can target the objective of grammar induction to a specific application. 1

This thesis is about estimating probabilistic models to uncover useful hidden structure in data; specifically, we address the problem of discovering syntactic structure in natural language text. We present three new parameter estimation techniques that generalize the standard approach, maximum likelihood estimation, in different ways. Contrastive estimation maximizes the conditional probability of the observed data given a “neighborhood” of implicit negative examples. Skewed deterministic annealing locally maximizes likelihood using a cautious parameter search strategy that starts with an easier optimization problem than likelihood, and iteratively moves to harder problems, culminating in likelihood. Structural annealing is similar, but starts with a heavy bias toward simple syntactic structures and gradually relaxes the bias. Our estimation methods do not make use of annotated examples. We consider their performance in both an unsupervised model selection setting, where models trained under different initialization and regularization settings are compared by evaluating the training objective on a small set of unseen, unannotated development data, and supervised model selection, where the most accurate model on the development set (now with annotations)

The lack of annotated data is an obstacle to the development of many natural language processing applications; the problem is especially severe when the data is non-English. Previous studies suggested the possibility of acquiring resources for non-English languages by bootstrapping from high quality English NLP tools and parallel corpora; however, the success of these approaches seems limited for dissimilar language pairs. In this paper, we propose a novel approach of combining a bootstrapped resource with a small amount of manually annotated data. We compare the proposed approach with other bootstrapping methods in the context of training a Chinese Part-of-Speech tagger. Experimental results show that our proposed approach achieves a significant improvement over EM and self-training and systems that are only trained on manual annotations. 1

Jointly parsing two languages has been shown to improve accuracies on either or both sides. However, its search space is much bigger than the monolingual case, forcing existing approaches to employ complicated modeling and crude approximations. Here we propose a much simpler alternative, bilingually-constrained monolingual parsing, where a source-language parser learns to exploit reorderings as additional observation, but not bothering to build the target-side tree as well. We show specifically how to enhance a shift-reduce dependency parser with alignment features to resolve shift-reduce conflicts. Experiments on the bilingual portion of Chinese Treebank show that, with just 3 bilingual features, we can improve parsing accuracies by 0.6 % (absolute) for both English and Chinese over a state-of-the-art baseline, with negligible (∼6%) efficiency overhead, thus much faster than biparsing. 1

Finite-state approaches have been highly successful at describing the morphological processes of many languages. Such approaches have largely focused on modeling the phone- or character-level processes that generate candidate lexical types, rather than tokens in context. For the full analysis of words in context, disambiguation is also required (Hakkani-Tür et al., 2000; Hajič et al., 2001). In this paper, we apply a novel source-channel model to the problem of morphological disambiguation (segmentation into morphemes, lemmatization, and POS tagging) for concatenative, templatic, and inflectional languages. The channel model exploits an existing morphological dictionary, constraining each word’s analysis to be linguistically valid. The source model is a factored, conditionally-estimated random field (Lafferty et al., 2001) that learns to disambiguate the full sentence by modeling local contexts. Compared with baseline state-of-the-art methods, our method achieves statistically significant error rate reductions on Korean, Arabic, and Czech, for various training set sizes and accuracy measures. 1

In morphologically rich languages, should morphological and syntactic disambiguation be treated sequentially or as a single problem? We describe several efficient, probabilistically interpretable ways to apply joint inference to morphological and syntactic disambiguation using lattice parsing. Joint inference is shown to compare favorably to pipeline parsing methods across a variety of component models. State-of-the-art performance on Hebrew Treebank parsing is demonstrated using the new method. The benefits of joint inference are modest with the current component models, but appear to increase as components themselves improve.

We describe a method for prediction of linguistic structure in a language for which only unlabeled data is available, using annotated data from a set of one or more helper languages. Our approach is based on a model that locally mixes between supervised models from the helper languages. Parallel data is not used, allowing the technique to be applied even in domains where human-translated texts are unavailable. We obtain state-of-theart performance for two tasks of structure prediction: unsupervised part-of-speech tagging and unsupervised dependency parsing. 1