We present an automatic approach to tree annotation in which basic nonterminal symbols are alternately split and merged to maximize the likelihood of a training treebank. Starting with a simple Xbar grammar, we learn a new grammar whose nonterminals are subsymbols of the original nonterminals. In contrast with previous work, we are able to split various terminals to different degrees, as appropriate to the actual complexity in the data. Our grammars automatically learn the kinds of linguistic distinctions exhibited in previous work on manual tree annotation. On the other hand, our grammars are much more compact and substantially more accurate than previous work on automatic annotation. Despite its simplicity, our best grammar achieves an F1 of 90.2 % on the Penn Treebank, higher than fully lexicalized systems. 1

We present several improvements to unlexicalized parsing with hierarchically state-split PCFGs. First, we present a novel coarse-to-fine method in which a grammar’s own hierarchical projections are used for incremental pruning, including a method for efficiently computing projections of a grammar without a treebank. In our experiments, hierarchical pruning greatly accelerates parsing with no loss in empirical accuracy. Second, we compare various inference procedures for state-split PCFGs from the standpoint of risk minimization, paying particular attention to their practical tradeoffs. Finally, we present multilingual experiments which show that parsing with hierarchical state-splitting is fast and accurate in multiple languages and domains, even without any language-specific tuning.

This paper documents a large set of heretofore unpublished details Collins used in his parser, such that, along with Collins' thesis (Collins, 1999), this paper contains all information necessary to duplicate Collins' benchmark results. Indeed, these as-yet-unpublished details account for an 11% relative reduction in error between a clean-room implementation of Collins' model and an implementation including all details. We also show a cleaner and equally--well-performing method for the handling of punctuation and conjunction, and reveal certain other probabilistic oddities about Collins' parser. We analyze not only the effect of the unpublished details, but also re-analyze the effect of certain well-known details, revealing that bilexical dependencies are barely used by the model and that head choice is not nearly as important to overall parsing performance as once thought. Finally, we perform experiments that show that the true discriminative power of lexicalization appears to lie in the fact that unlexicalized syntactic structures are generated conditioning on the head word and its part of speech

This paper defines a generative probabilistic model of parse trees, which we call PCFG-LA. This model is an extension of PCFG in which non-terminal symbols are augmented with latent variables. Finegrained CFG rules are automatically induced from a parsed corpus by training a PCFG-LA model using an EM-algorithm. Because exact parsing with a PCFG-LA is NP-hard, several approximations are described and empirically compared. In experiments using the Penn WSJ corpus, our automatically trained model gave a performance of 86.6 % (F ¥ , sentences ¦ 40 words), which is comparable to that of an unlexicalized PCFG parser created using extensive manual feature selection.

We present a detailed investigation of the challenges posed when applying parsing models developed against English corpora to Chinese. We develop a

With syntactically annotated corpora becoming increasingly available for a variety of languages and grammatical frameworks, tree query tools have proven invaluable to linguists and computer scientists for both data exploration and corpusbased research. We provide a combined engine for tree query (Tregex) and manipulation (Tsurgeon) that can operate on arbitrary tree data structures with no need for preprocessing. Tregex remedies several expressive and implementational limitations of existing query tools, while Tsurgeon is to our knowledge the most expressive tree manipulation utility available. 1.

Abstract. We build a class-based selection preference sub-model to incorporate external semantic knowledge from two Chinese electronic semantic dictionaries. This sub-model is combined with modifier-head generation sub-model. After being optimized on the held out data by the EM algorithm, our improved parser achieves 79.4 % (F1 measure), as well as a 4.4 % relative decrease in error rate on the Penn Chinese Treebank (CTB). Further analysis of performance improvement indicates that semantic knowledge is helpful for nominal compounds, coordination, and N⋄V tagging disambiguation, as well as alleviating the sparseness of information available in treebank. 1

A notable gap in research on statistical dependency parsing is a proper conditional probability distribution over nonprojective dependency trees for a given sentence. We exploit the Matrix Tree Theorem (Tutte, 1984) to derive an algorithm that efficiently sums the scores of all nonprojective trees in a sentence, permitting the definition of a conditional log-linear model over trees. While discriminative methods, such as those presented in McDonald et al. (2005b), obtain very high accuracy on standard dependency parsing tasks and can be trained and applied without marginalization, “summing trees ” permits some alternative techniques of interest. Using the summing algorithm, we present competitive experimental results on four nonprojective languages, for maximum conditional likelihood estimation, minimum Bayes-risk parsing, and hidden variable training. 1

We present two methods for incorporating detailed features in a Spanish parser, building on a baseline model that is a lexicalized PCFG. The first method exploits Spanish morphology, and achieves an F1 constituency score of 83.6%. This is an improvement over 81.2 % accuracy for the baseline, which makes little or no use of morphological information. The second model uses a reranking approach to add arbitrary global features of parse trees to the morphological model. The reranking model reaches 85.1 % F1 accuracy on the Spanish parsing task. The resulting model for Spanish parsing combines an approach that specifically targets morphological information with an approach that makes use of general structural features.

Tree substitution grammars (TSGs) offer many advantages over context-free grammars (CFGs), but are hard to learn. Past approaches have resorted to heuristics. In this paper, we learn a TSG using Gibbs sampling with a nonparametric prior to control subtree size. The learned grammars perform significantly better than heuristically extracted ones on parsing accuracy. 1