Francis Bond

Enhancing the Japanese WordNet

The Japanese WordNet currently has 51,000 synsets with Japanese entries. In this paper, we discuss three methods of extending it: increasing the cover, linking it to examples in corpora and linking it to other resources (SUMO and GoiTaikei). In addition, we outline our plans to make it more useful by adding Japanese definition sentences to each synset. Finally, we discuss how releasing the corpus under an open license has led to the construction of interfaces in a variety of programming languages.

Memory-based learning for article generation

Article choice can pose difficult problems in applications such as machine translation and automated summarization. In this paper, we investigate the use of corpus data to collect statistical generalizations about article use in English in order to be able to generate articles automatically to supplement a symbolic generator. We use data from the Penn Treebank as input to a memory-based learner (TiMBL 3.0; Daelemans et al., 2000) which predicts whether to generate an article with respect to an English base noun phrase. We discuss competitive results obtained using a variety of lexical, syntactic and semantic features that play an important role in automated article generation.

A Hybrid Rule and Example-based Method for Machine Translation

This paper introduces a new example-based method of machine translation in which the examples need not be direct translations. The system will weed out strange examples during translation, allowing the use of currently available sentence-aligned corpora as data. Rule-based modules are used where appropriate. A prototype Japanese-to-English system has been implemented that allows multiple users to share corpora.

Learning the Countability of English Nouns from Corpus Data

This paper describes a method for learning the countability preferences of English nouns from raw text corpora. The method maps the corpus-attested lexico-syntactic properties of each noun onto a feature vector, and uses a suite of memory-based classifiers to predict membership in 4 countability classes. We were able to assign countability to English nouns with a precision of 94.6%.

The hinoki treebank a treebank for text understanding

In this paper we describe the motivation for and construction of a new Japanese lexical resource: the Hinoki treebank. The treebank is built from dictionary definition sentences, and uses an HPSG grammar to encode the syntactic and semantic information. We then show how this treebank can be used to extract thesaurus information from definition sentences in a language-neutral way using minimal recursion semantics.

Editorial: Introduction to the special issue on multiword expressions: Having a crack at a hard nut

Multiword expressions are an integral part of language. Their heterogeneous characteristics have proved a challenge to both linguistic and computational analysis. Their importance to language technology has long been recognised. In this special issue we include ten papers which propose a variety of approaches for finding and handling these expressions, both for building general purpose lexical resources and in the context of specific applications. In this introduction we give a brief summary of what multiword expressions are, the challenges that they pose and some open areas of research. We then highlight the contributions that the ten papers make to these areas.

Countability and number in Japanese to English machine translation

This paper presents a heuristic method that uses information in the Japanese text along with knowledge of English countability and number stored in transfer dictionaries to determine the countability and number of English noun phrases. Incorporating this method into the machine translation system ALT-J/E, helped to raise the percentage of noun phrases generated with correct use of articles and number from 65% to 73%.

In Search of a Systematic Treatment of Determinerless PPs

This paper examines Determinerless PPs in English from a theoretical perspective. We classify attested P + N combinations across a number of analytic dimensions, arguing that the observed cases fall into at least three distinct classes. We then survey three different analytic methods that can predict the behaviour of the differing classes and examine various remaining difficult cases that may remain as challenges.

A plethora of methods for learning English countability

This paper compares a range of methods for classifying words based on linguistic diagnostics, focusing on the task of learning countabilities for English nouns. We propose two basic approaches to feature representation: distribution-based representation, which simply looks at the distribution of features in the corpus data, and agreement-based representation which analyses the level of token-wise agreement between multiple preprocessor systems. We additionally compare a single multiclass classifier architecture with a suite of binary classifiers, and combine analyses from multiple preprocessors. Finally, we present and evaluate a feature selection method.

Combining linguistic resources to create a machine-tractable Japanese-Malay dictionary

We present a method for combining two bilingual dictionaries to make a third, using one language as a pivot. In this case we combine a Japanese-English dictionary with a Malay-English dictionary, to produce a Japanese-Malay dictionary. Our method differs from previous methods in its improved matching through normalization of the pivot language. We have made a prototype dictionary of around 76,000 Japanese-Malay pairs for 50,000 Japanese head words.