We formulate dependency parsing as a graphical model with the novel ingredient of global constraints. We show how to apply loopy belief propagation (BP), a simple and effective tool for approximate learning and inference. As a parsing algorithm, BP is both asymptotically and empirically efficient. Even with second-order features or latent variables, which would make exact parsing considerably slower or NP-hard, BP needs only O(n3) time with a small constant factor. Furthermore, such features significantly improve parse accuracy over exact first-order methods. Incorporating additional features would increase the runtime additively rather than multiplicatively. 1

We present posterior regularization, a probabilistic framework for structured, weakly supervised learning. Our framework efficiently incorporates indirect supervision via constraints on posterior distributions of probabilistic models with latent variables. Posterior regularization separates model complexity from the complexity of structural constraints it is desired to satisfy. By directly imposing decomposable regularization on the posterior moments of latent variables during learning, we retain the computational efficiency of the unconstrained model while ensuring desired constraints hold in expectation. We present an efficient algorithm for learning with posterior regularization and illustrate its versatility on a diverse set of structural constraints such as bijectivity, symmetry and group sparsity in several large scale experiments, including multi-view learning, cross-lingual dependency grammar induction, unsupervised part-of-speech induction, and bitext word alignment. 1

We present experiments with a dependency parsing model defined on rich factors. Our model represents dependency trees with factors that include three types of relations between the tokens of a dependency and their children. We extend the projective parsing algorithm of Eisner (1996) for our case, and train models using the averaged perceptron. Our experiments show that considering higher-order information yields significant improvements in parsing accuracy, but comes at a high cost in terms of both time and memory consumption. In the multilingual exercise of the CoNLL-2007 shared task (Nivre et al., 2007), our system obtains the best accuracy for English, and the second best accuracies for Basque and Czech. 1

Background: Extracting Protein-Protein Interactions (PPI) from research papers is a way of translating information from English to the language used by the databases that store this information. With recent advances in automatic PPI detection, it is now possible to speed up this process considerably. Syntactic features from different parsers for biomedical English text are readily available, and can be used to improve the performance of such PPI extraction systems. Results: A complete PPI system was built. It uses a deep syntactic parser to capture the semantic meaning of the sentences, and a shallow dependency parser to improve the performance further. Machine learning is used to automatically make rules to extract pairs of interacting proteins from the semantics of the sentences. The results have been evaluated using the AImed corpus, and they are better than earlier published results. The F-score of the current system is 69.5 % for cross-validation between pairs that may come from the same abstract, and 52.0% when complete abstracts are hidden until final testing. Automatic 10-fold cross-validation on the entire AImed corpus can be done in less than 45 minutes on a single server. We also present some previously unpublished statistics about the AImed corpus, and a short analysis of the AImed representation language. Conclusions: We present a PPI extraction system, using different syntactic parsers to extract features for SVM

Broad-coverage annotated treebanks necessary to train parsers do not exist for many resource-poor languages. The wide availability of parallel text and accurate parsers in English has opened up the possibility of grammar induction through partial transfer across bitext. We consider generative and discriminative models for dependency grammar induction that use word-level alignments and a source language parser (English) to constrain the space of possible target trees. Unlike previous approaches, our framework does not require full projected parses, allowing partial, approximate transfer through linear expectation constraints on the space of distributions over trees. We consider several types of constraints that range from generic dependency conservation to language-specific annotation rules for auxiliary verb analysis. We evaluate our approach on Bulgarian and Spanish CoNLL shared task data and show that we consistently outperform unsupervised methods and can outperform supervised learning for limited training data. 1

For the 11th straight year, the Conference on Computational Natural Language Learning has been accompanied by a shared task whose purpose is to promote natural language processing applications and evaluate them in a standard setting. In 2009, the shared task was dedicated to the joint parsing of syntactic and semantic dependencies in multiple languages. This shared task combines the shared tasks of the previous five years under a unique dependency-based formalism similar to the 2008 task. In this paper, we define the shared task, describe how the data sets were created and show their quantitative properties, report the results and summarize the approaches of the participating systems.

We present a novel deterministic dependency parsing algorithm that attempts to create the easiest arcs in the dependency structure first in a non-directional manner. Traditional deterministic parsing algorithms are based on a shift-reduce framework: they traverse the sentence from left-to-right and, at each step, perform one of a possible set of actions, until a complete tree is built. A drawback of this approach is that it is extremely local: while decisions can be based on complex structures on the left, they can look only at a few words to the right. In contrast, our algorithm builds a dependency tree by iteratively selecting the best pair of neighbours to connect at each parsing step. This allows incorporation of features from already built structures both to the left and to the right of the attachment point. The parser learns both the attachment preferences and the order in which they should be performed. The result is a deterministic, best-first, O(nlogn) parser, which is significantly more accurate than best-first transition based parsers, and nears the performance of globally optimized parsing models. 1

We describe a two-stage optimization of the MaltParser system for the ten languages in the multilingual track of the CoNLL 2007 shared task on dependency parsing. The first stage consists in tuning a single-parser system for each language by optimizing parameters of the parsing algorithm, the feature model, and the learning algorithm. The second stage consists in building an ensemble system that combines six different parsing strategies, extrapolating from the optimal parameters settings for each language. When evaluated on the official test sets, the ensemble system significantly outperforms the single-parser system and achieves the highest average labeled attachment score. 1

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

To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories. In addition to the tagset, we develop a mapping from 25 different treebank tagsets to this universal set. As a result, when combined with the original treebank data, this universal tagset and mapping produce a dataset consisting of common parts-of-speech for 22 different languages. We highlight the use of this resource via three experiments, that (1) compare tagging accuracies across languages, (2) present an unsupervised grammar induction approach that does not use gold standard part-of-speech tags, and (3) use the universal tags to transfer dependency parsers between languages, achieving state-of-the-art results.