Dependency parsing is a central NLP task. In this paper we show that the common evaluation for unsupervised dependency parsing is highly sensitive to problematic annotations. We show that for three leading unsupervised parsers (Klein and Manning, 2004; Cohen and Smith, 2009; Spitkovsky et al., 2010a), a small set of parameters can be found whose modification yields a significant improvement in standard evaluation measures. These parameters correspond to local cases where no linguistic consensus exists as to the proper gold annotation. Therefore, the standard evaluation does not provide a true indication of algorithm quality. We present a new measure, Neutral Edge Direction (NED), and show that it greatly reduces this undesired phenomenon. 1

A strong inductive bias is essential in unsupervised grammar induction. In this paper, we explore a particular sparsity bias in dependency grammars that encourages a small number of unique dependency types. We use part-of-speech (POS) tags to group dependencies by parent-child types and investigate sparsity-inducing penalties on the posterior distributions of parent-child POS tag pairs in the posterior regularization (PR) framework of Graça et al. (2007). In experiments with 12 different languages, we achieve significant gains in directed accuracy over the standard expectation maximization (EM) baseline for 9 of the languages, with an average accuracy improvement of 6%. Further, we show that for 8 out of 12 languages, the new method outperforms models based on standard Bayesian sparsity-inducing parameter priors, with an average improvement of 4%. On English text in particular, we show that our approach improves performance over other state of the art techniques.

We show how punctuation can be used to improve unsupervised dependency parsing. Our linguistic analysis confirms the strong connection between English punctuation and phrase boundaries in the Penn Treebank. However, approaches that naively include punctuation marks in the grammar (as if they were words) do not perform well with Klein and Manning’s Dependency Model with Valence (DMV). Instead, we split a sentence at punctuation and impose parsing restrictions over its fragments. Our grammar inducer is trained on the Wall Street Journal (WSJ) and achieves 59.5 % accuracy out-of-domain (Brown sentences with 100 or fewer words), more than 6 % higher than the previous best results. Further evaluation, using the 2006/7 CoNLL sets, reveals that punctuation aids grammar induction in 17 of 18 languages, for an overall average net gain of 1.3%. Some of this improvement is from training, but more than half is from parsing with induced constraints, in inference. Punctuation-aware decoding works with existing (even already-trained) parsing models and always increased accuracy in our experiments. 1

Clustering is crucial for many NLP tasks and applications. However, evaluating the results of a clustering algorithm is hard. In this paper we focus on the evaluation setting in which a gold standard solution is available. We discuss two existing information theory based measures, V and VI, and show that they are both hard to use when comparing the performance of different algorithms and different datasets. The V measure favors solutions having a large number of clusters, while the range of scores given by VI depends on the size of the dataset. We present a new measure, NVI, which normalizes VI to address the latter problem. We demonstrate the superiority of NVI in a large experiment involving an important NLP application, grammar induction, using real corpus data in English, German and Chinese. 1

Sets of lexical items sharing a significant aspect of their meaning (concepts) are fundamental for linguistics and NLP. Unsupervised concept acquisition algorithms have been shown to produce good results, and are preferable over manual preparation of concept resources, which is labor intensive, error prone and somewhat arbitrary. Some existing concept mining methods utilize supervised language-specific modules such as POS taggers and computationally intensive parsers. In this paper we present an efficient fully unsupervised concept acquisition algorithm that uses syntactic information obtained from a fully unsupervised parser. Our algorithm incorporates the bracketings induced by the parser into the meta-patterns used by a symmetric patterns and graph-based concept discovery algorithm. We evaluate our algorithm on very large corpora in English and Russian, using both human judgments and WordNetbased evaluation. Using similar settings as the leading fully unsupervised previous work, we show a significant improvement in concept quality and in the extraction of multiword expressions. Our method is the first to use fully unsupervised parsing for unsupervised concept discovery, and requires no languagespecific tools or pattern/word seeds. 1

Clustering is a central technique in NLP. Consequently, clustering evaluation is of great importance. Many clustering algorithms are evaluated by their success in tagging corpus tokens. In this paper we discuss type level evaluation, which reflects class membership only and is independent of the token statistics of a particular reference corpus. Type level evaluation casts light on the merits of algorithms, and for some applications is a more natural measure of the algorithm’s quality. We propose new type level evaluation measures that, contrary to existing measures, are applicable when items are polysemous, the common case in NLP. We demonstrate the benefits of our measures using a detailed case study, POS induction. We experiment with seven leading algorithms, obtaining useful insights and showing that token and type level measures can weakly or even negatively correlate, which underscores the fact that these two approaches reveal different aspects of clustering quality. 1

We present a novel approach to distributionalonly, fully unsupervised, POS tagging, based on an adaptation of the EM algorithm for the estimation of a Gaussian mixture. In this approach, which we call Latent-Descriptor Clustering (LDC), word types are clustered using a series of progressively more informative descriptor vectors. These descriptors, which are computed from the immediate left and right context of each word in the corpus, are updated based on the previous state of the cluster assignments. The LDC algorithm is simple and intuitive. Using standard evaluation criteria for unsupervised POS tagging, LDC shows a substantial improvement in performance over state-of-the-art methods, along with a several-fold reduction in computational cost. 1

We consider the problem of fully unsupervised learning of grammatical (part-of-speech) categories from unlabeled text. The standard maximum-likelihood hidden Markov model for this task performs poorly, because of its weak inductive bias and large model capacity. We address this problem by refining the model and modifying the learning objective to control its capacity via parametric and non-parametric constraints. Our approach enforces word-category association sparsity, adds morphological and orthographic features, and eliminates hard-to-estimate parameters for rare words. We develop an efficient learning algorithm that is not much more computationally intensive than standard training and provide an open-source implementation. Our experiments on five diverse languages (Bulgarian, Danish, English, Portuguese, Spanish) achieve significant improvements compared with previous methods for the same task. 1.