Logo Logo
Help
Contact
Switch Language to German

Poerner, Nina; Sabet, Masoud Jalili; Roth, Benjamin and Schütze, Hinrich (October 2018): Aligning Very Small Parallel Corpora Using Cross-Lingual Word Embeddings and a Monogamy Objective. [PDF, 409kB]

Abstract

Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora. We therefore present an alternative approach based on cross-lingual word embeddings (CLWEs), which are trained on purely monolingual data. Our main contribution is an unsupervised objective to adapt CLWEs to parallel corpora. In experiments on between 25 and 500 sentences, our method outperforms fast-align. We also show that our fine-tuning objective consistently improves a CLWE-only baseline.

Actions (login required)

View Item View Item