Compiling a Massive, Multilingual Dictionary via Probabilistic Inference

Can we automatically compose a large set of Wiktionaries and translation dictionaries to yield a massive, multilingual dictionary whose coverage is substantially greater than that of any of its constituent dictionaries? The composition of multiple translation dictionaries leads to a transitive inference problem: if word A translates to word B which in turn translates to word C, what is the probability that C is a translation of A? The paper introduces a novel algorithm that solves this problem for 10,000,000 words in more than 1,000 languages. The algorithm yields PANDICTIONARY, a novel multilingual dictionary. PANDICTIONARY contains more than four times as many translations than in the largest Wiktionary at precision 0.90 and over 200,000,000 pairwise translations in over 200,000 language pairs at precision 0.8.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Mausam, Stephen Soderland, Oren Etzioni, Daniel S. Weld, Michael Skinner, Jeff Bilmes
• Keywords: ACL 2009, Computational Linguistics, Dictionaries, Multilingual Dictionary, Transitive Inference Problem