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,

A key question facing the parsing community is how to compare parsers which use different grammar formalisms and produce different output. Evaluating a parser on the same resource used to create it can lead to non-comparable accuracy scores and an over-optimistic view of parser performance. In this paper we evaluate a CCG parser on DepBank, and demonstrate the difficulties in converting the parser output into Dep-Bank grammatical relations. In addition we present a method for measuring the effectiveness of the conversion, which provides an upper bound on parsing accuracy. The CCG parser obtains an F-score of 81.9% on labelled dependencies, against an upper bound of 84.8%. We compare the CCG parser against the RASP parser, outperforming RASP by over 5 % overall and on the majority of dependency types. 1

The C&C CCG parser is a highly efficient linguistically motivated parser. The efficiency is achieved using a tightly-integrated supertagger, which assigns CCG lexical categories to words in a sentence. The integration allows the parser to request more categories if it cannot find a spanning analysis. We present several enhancements to the CKY chart parsing algorithm used by the parser. The first proposal is chart repair, which allows the chart to be efficiently updated by adding lexical categories individually, and we evaluate several strategies for adding these categories. The second proposal is to add constraints to the chart which require certain spans to be constituents. Finally, we propose partial beam search to further reduce the search space. Overall, the parsing speed is improved by over 35 % with negligible loss of accuracy or coverage. 1

This paper explores the kinds of probabilistic relations that are important in syntactic disambiguation. It proposes that two widely used kinds of relations, lexical dependencies and structural relations, have complementary disambiguation capabilities. It presents a new model based on structural relations, the Tree-gram model, and reports experiments showing that structural relations should bene t from enrichment by lexical dependencies

Scalable syntactic processing will underpin the sophisticated language technology needed for next generation information access. Companies are already using nlp tools to create web-scale question answering and “semantic search” engines. Massive amounts of parsed web data will also allow the automatic creation of semantic knowledge resources on an unprecedented scale. The web is a challenging arena for syntactic parsing, because of its scale and variety of styles, genres, and domains. The goals of our workshop were to scale and adapt an existing wide-coverage parser to Wikipedia text; improve the efficiency of the parser through various methods of chart pruning; use self-training to improve the efficiency and accuracy of the parser; use the parsed wiki data for an innovative form of bootstrapping to make the parser both more efficient and more accurate; and finally use the parsed web data for improved disambiguation of coordination structures, using a variety of syntactic and semantic knowledge sources. The focus of the research was the c&c parser (Clark and Curran, 2007c), a stateof-the-art statistical parser based on Combinatory Categorial Grammar (ccg). The parser has been evaluated on a number of standard test sets achieving state-of-the-art accuracies. It has also recently been adapted successfully to the biomedical domain (Rimell and Clark, 2009). The parser is surprisingly efficient, given its detailed output, processing tens of sentences per second. For web-scale text processing, we aimed to make the parser an order of magnitude faster still. The c&c parser is one of only very few parsers currently available which has the potential to produce detailed, accurate analyses at the scale we were considering.

Bangalore and Joshi (1999) investigate supertagging as “almost parsing”. In this paper we explore this claim further by replacing their Lightweight Dependency Analyzer with a nonlexical probabilistic chart parser. Our approach is still in the spirit of their work in the sense that lexical information is only used during supertagging; the parser and its probabilistic model only see supertags. 1