Minimally supervised lemmatization scheme induction through bilingual parallel corpora

We present a lemma induction scheme on a target language through minimally supervised alignment and transfer methods utilizing English-to-German parallel corpora. Compared to previous alignment and transfer approaches, the approach outlined here increases computational efficiency and significantly reduces the level of supervision necessary in inducing clusters of inflectional forms. Furthermore, we increase our search field to include not only verbs but also nouns and adjectives in the target language, and achieve comparable results to previous unsupervised monolingual methods.