The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent coreference, quantification, and many other higher-order phenomena, but also broad, in that it covers every instance of every verb in the corpus and allows representative statistics to be calculated. We discuss the criteria used to define the sets of semantic roles used in the annotation process and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty ‘‘trace’ ’ categories of the treebank.

This paper describes and evaluates log-linear parsing models for Combinatory Categorial Grammar (CCG). A parallel implementation of the L-BFGS optimisation algorithm is described, which runs on a Beowulf cluster allowing the complete Penn Treebank to be used for estimation. We also develop a new efficient parsing algorithm for CCG which maximises expected recall of dependencies. We compare models which use all CCG derivations, including nonstandard derivations, with normal-form models. The performances of the two models are comparable and the results are competitive with existing wide-coverage CCG parsers.

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 describes a number of log-linear parsing models for an automatically extracted lexicalized grammar. The models are "full" parsing models in the sense that probabilities are defined for complete parses, rather than for independent events derived by decomposing the parse tree. Discriminative training is used to estimate the models, which requires incorrect parses for each sentence in the training data as well as the correct parse. The lexicalized grammar formalism used is Combinatory Categorial Grammar (CCG), and the grammar is automatically extracted from CCGbank, a CCG version of the Penn Treebank. The combination of discriminative training and an automatically extracted grammar leads to a significant memory requirement (over 20 GB), which is satisfied using a parallel implementation of the BFGS optimisation algorithm running on a Beowulf cluster. Dynamic programming over a packed chart, in combination with the parallel implementation, allows us to solve one of the largest-scale estimation problems in the statistical parsing literature in under three hours. A key component of the parsing system, for both training and testing, is a Maximum Entropy supertagger which assigns CCG lexical categories to words in a sentence. The supertagger makes the discriminative training feasible, and also leads to a highly efficient parser. Surprisingly,

In this paper, we describe an implemented system that utilizes combinatory categorial grammar known to be competent in modeling natural language, with a controlled mechanism for the parser to operate bidirectionally and incrementally. We discuss the performance of the system on a large set of abstracts in MEDLINE with quite encouraging results.

This paper shows how to construct semantic representations from the derivations produced by a wide-coverage CCG parser. Unlike the dependency structures returned by the parser itself, these can be used directly for semantic interpretation. We demonstrate that well-formed semantic representations can be produced for over 97 % of the sentences in unseen WSJ text. We believe this is a major step towards widecoverage semantic interpretation, one of the key objectives of the field of NLP. 1

The paper shows how Combinatory Categorial Grammar (CCG) can be adapted to take advantage of the extra resourcesensitivity provided by the Categorial Type Logic framework. The resulting reformulation, Multi-Modal CCG, supports lexically specified control over the applicability of combinatory rules, permitting a universal role component and shedding the need for language-specific restrictions on rules. We discuss some of the linguistic motivation for these changes, define the Multi-Modal CCG system and demonstrate how it works on some basic examples. We furthermore outline some possible extensions and address computational aspects of Multi-Modal CCG.

We present a detailed process theory of the moment-by-moment working-memory retrievals and associated control structure that subserve sentence comprehension. The theory is derived from the application of independently motivated principles of memory and cognitive skill to the specialized task of sentence parsing. The resulting theory construes sentence processing as a series of skilled associative memory retrievals modulated by similarity-based interference and fluctuating activation. The cognitive principles are formalized in computational form in the Adaptive Control of Thought–Rational (ACT–R) architecture, and our process model is realized in ACT–R. We present the results of 6 sets of simulations: 5 simulation sets provide quantitative accounts of the effects of length and structural interference on both unambiguous and garden-path structures. A final simulation set provides a graded taxonomy of double center embeddings ranging from relatively easy to extremely difficult. The explanation of center-embedding difficulty is a novel one that derives from the model’s complete reliance on discriminating retrieval cues in the absence of an explicit representation of serial order information. All fits were obtained with only 1 free scaling parameter fixed across the simulations; all other parameters were ACT–R defaults. The modeling results support the hypothesis that fluctuating activation and similarity-based interference are the key factors shaping working memory in sentence processing. We contrast the theory and empirical predictions with several related accounts of sentence-processing complexity.

This paper investigates two elements of Maximum Entropy tagging: the use of a correction feature in the Generalised Iterative Scaling (GIS) estimation algorithm, and techniques for model smoothing. We show analytically and empirically that the correction feature, assumed to be required for the correctness of GIS, is unnecessary. We also explore the use of a Gaussian prior and a simple cutoff for smoothing. The experiments are performed with two tagsets: the standard Penn Treebank POS tagset and the larger set of lexical types from Combinatory Categorial Grammar. 1

Wide-coverage and robust NLP techniques always seemed to go hand in hand with shallow analyses. This was certainly true a couple of years ago,