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.

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,

This paper describes the role of supertagging in a wide-coverage CCG parser which uses a log-linear model to select an analysis. The supertagger reduces the derivation space over which model estimation is performed, reducing the space required for discriminative training. It also dramatically increases the speed of the parser. We show that large increases in speed can be obtained by tightly integrating the supertagger with the CCG grammar and parser. This is the first work we are aware of to successfully integrate a supertagger with a full parser which uses an automatically extracted grammar. We also further reduce the derivation space using constraints on category combination. The result is an accurate wide-coverage CCG parser which is an order of magnitude faster than comparable systems for other linguistically motivated formalisms.

This paper describes log-linear parsing models for Combinatory Categorial Grammar (CCG). Log-linear models can easily encode the long-range dependencies inherent in coordination and extraction phenomena, which CCG was designed to handle. Log-linear models have previously been applied to statistical parsing, under the assumption that all possible parses for a sentence can be enumerated. Enumerating all

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

We present a novel approach for finding discontinuities that outperforms previously published results on this task. Rather than using a deeper grammar formalism, our system combines a simple unlexicalized PCFG parser with a shallow pre-processor. This pre-processor, which we call a trace tagger, does surprisingly well on detecting where discontinuities can occur without using phase structure information.

This paper describes an extremely lexicalized probabilistic model for fast and accurate HPSG parsing. In this model, the probabilities of parse trees are defined with only the probabilities of selecting lexical entries. The proposed model is very simple, and experiments revealed that the implemented parser runs around four times faster than the previous model and that the proposed model has a high accuracy comparable to that of the previous model for probabilistic HPSG, which is defined over phrase structures. We also developed a hybrid of our probabilistic model and the conventional phrasestructure-based model. The hybrid model is not only significantly faster but also significantly more accurate by two points of precision and recall compared to the previous model. 1

The limited coverage of lexical-semantic resources is a significant problem for NLP systems which can be alleviated by automatically classifying the unknown words. Supersense tagging assigns unknown nouns one of 26 broad semantic categories used by lexicographers to organise their manual insertion into WORDNET. Ciaramita and Johnson (2003) present a tagger which uses synonym set glosses as annotated training examples. We describe an unsupervised approach, based on vector-space similarity, which does not require annotated examples but significantly outperforms their tagger. We also demonstrate the use of an extremely large shallow-parsed corpus for calculating vector-space semantic similarity.

We investigate the task of learning models for visual object recognition from natural language descriptions alone. The approach contributes to the recognition of fine-grain object categories, such as animal and plant species, where it may be difficult to collect many images for training, but where textual descriptions of visual attributes are readily available. As an example we tackle recognition of butterfly species, learning models from descriptions in an online nature guide. We propose natural language processing methods for extracting salient visual attributes from these descriptions to use as ‘templates ’ for the object categories, and apply vision methods to extract corresponding attributes from test images. A generative model is used to connect textual terms in the learnt templates to visual attributes. We report experiments comparing the performance of humans and the proposed method on a dataset of ten butterfly categories. 1

This paper presents results in automated genre classification of digital documents in PDF format. It describes genre classification as an important ingredient in contextualising scientific data and in retrieving targetted material for improving research. The current paper compares the role of visual layout, stylistic features and language model features in clustering documents and presents results in retrieving five selected genres (Scientific Article, Thesis, Periodicals, Business Report, and Form) from a pool of materials populated with documents of the nineteen most popular genres found in our experimental data set.