Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monoling...

This paper describes the official runs of the Twenty-One group for CLEF-2000. The Twenty-One group participated in the monolingual, bilingual and multilingual tasks. The following new techniques are introduced in this paper. In the bilingual task we experimented with different methods to estimate translation probabilities. In the multilingual task we experimented with refinements on raw-score m...

A new approach to handle unknown words in machine translation is presented. The basic idea is to find definitions for the unknown words on the source language side and translate those definitions instead. Only monolingual resources are required, which generally offer a broader coverage than bilingual resources and are available for a large number of languages. In order to use this in a machine ...

The Innovations of the English learner's dictionary are wellknown and Justly praised, but some authorities have begun to question the Anglo-Saxon ethnocentriclty of these monolingual dictionaries and wondered If thls genre Is Ideal for foreign learners, WhIIe we should avoid the extreme fallacy of the one-to-one lexk:al equivalent which constitutes the maln limitation of the traditional blllngu...

This paper presents recent results of the ongoing project aimed at creating the nominal database of the Hungarian WordNet. We present 9 different automatic methods, developed for linking Hungarian nouns to WN 1.6 synsets. Nominal entries are obtained from two different machine-readable dictionaries, a bilingual EnglishHungarian and an explanatory monolingual (Hungarian). The results are evaluat...

This chapter focuses on unsupervised corpus-based methods of word sense discrimination that are knowledge-lean, and do not rely on external knowledge sources such as machine readable dictionaries, concept hierarchies, or sense-tagged text. They do not assign sense tags to words; rather, they discriminate among word meanings based on information found in unannotated corpora. This chapter reviews...

The availability of machine-readable bilingual linguistic resources is crucial not only for machine translation but also for other applications such as cross-lingual information retrieval. However, the building of such resources demands extensive manual work. This paper describes a methodology to build automatically bilingual dictionaries and transfer rules by extracting knowledge from word-ali...

This chapter focuses on unsupervised corpus-based methods of word sense discrimination that are knowledge-lean, and do not rely on external knowledge sources such as machine readable dictionaries, concept hierarchies, or sense-tagged text. They do not assign sense tags to words; rather, they discriminate among word meanings based on information found in unannotated corpora. This chapter reviews...

The availability of machine-readable bilingual linguistic resources is crucial not only for machine translation but also for other applications such as cross-lingual information retrieval. However, the building of such resources demands extensive manual work. This paper describes a methodology to build automatically bilingual dictionaries and transfer rules by extracting knowledge from word-ali...

Named entity phrases are some of the most difficult phrases to translate because new phrases can appear from nowhere, and because many are domain specific, not to be found in bilingual dictionaries. We present a novel algorithm for translating named entity phrases using easily obtainable monolingual and bilingual resources. We report on the application and evaluation of this algorithm in transl...