Methods dealing with bilingual lexicon extraction from comparable corpora are often based on word co-occurrence observation and are by essence more effective when using large corpora. In most cases, specialized comparable corpora are of small size, and this particularity has a direct impact on bilingual terminology extraction results. In order to overcome insufficient data coverage and to make word co-occurrence statistics more reliable, we propose building a predictive model of word co-occurrence counts. We compare different predicting models with the traditional Standard Approach and show that once we have identified the best procedures, our method increases significantly the performance of extracting word translations from comparable corpora.