Recently, many projects have been proposed aiming at automatically transforming the multilingual information available on parallel texts into linguistic knowledge useful for machine translation. This paper describes an ongoing PhD project in which the main goal is to automatically induce transfer rules and bilingual dictionaries from part-of-speech tagged and lexically aligned parallel corpora....

Bilingual dictionaries provide meaning associations between the words of two languages, those of an ideal bilingual speaker. Learners can use these associations to look up foreign equivalents of known native words, but are forced to use script-based lookup methods when faced with unknown foreign words. This paper presents the Pinyomi Chinese-Japanese dictionary interface, which uses a novel met...

In this paper, we present an unsupervised hybrid model which combines statistical, lexical, linguistic, contextual, and temporal features in a generic EMbased framework to harvest bilingual terminology from comparable corpora through comparable document alignment constraint. The model is configurable for any language and is extensible for additional features. In overall, it produces considerabl...

Movie subtitle alignment is a potentially useful approach for deriving automatically parallel bilingual/multilingual spoken language data for automatic speech translation. In this paper, we consider the movie subtitle alignment task. We propose a distance metric between utterances of different languages based on lexical features derived from bilingual dictionaries. We use the dynamic time warpi...

This paper describes the official runs of the Twenty-One group for the first CLEF workshop. 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 ...

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...

In this paper we present experiments concerned with automatically learning bilingual resources for machine translation: bilingual dictionaries and transfer rules. The experiments were carried out with Brazilian Portuguese (pt), English (en) and Spanish (es) texts in two parallel corpora: pt–en and pt–es. They were designed to investigate the relevance of two factors in the induction process, na...

Chinese, Japanese and Arabic bilingual dictionaries suffer from shortcomings rarely seen in works of other major languages. These include archaic headwords and senses, an overly prescriptive approach, learner-unfriendly sense ordering, and the omission of important multiword expressions. This paper describes how three bilingual learner’s dictionaries address these issues, focusing on compilatio...