Disambiguated Translation are now systematically computed

After a long wait, I finally managed to integrate the “Source Translation Disambiguation” experiment into DBnary extractor. Hence the sources of some translation are disambiguated each time a new dump is extracted. What is this ? In wiktionary, translations are sometimes included in a box which corresponds to a word sense. It allows for distinguishing between different translations. For instance, the French noun “bleu” may be translated in “blue” when it means a color, in “bruise” when it is used in the “small injury” acception and “rookie” when it designs a non experimented soldier.

Read More

METEOR with DBNARY

The DBnary dataset has been used for an experiment on a Machine Translation Quality measure based on METEOR. The research paper will be presented during MT-Summit 2016. For work replication, we provide the sources of the experiment: full source code + data on dropbox

Read More

Translations are now connected to word senses

A translation is supposed to connect a source word sense to a target word sense. However, current DBnary data connects a lexical entry to a target string. By using available glosses, we are able to connect translations to their source word sense. We evaluate the accuracy of these relations to over 80%.

Read More

Finnish translation extractor improved

The Finnish language edition recently used a new way to encode translations. Hence, the extractor’s performance was reduced (as may be seen in the Finnish Stats). The extrator has been adapted to deal with the new translation encoding and extraction rate is now back to normal.

Read More