Aligning Very Small Parallel Corpora Using Cross-Lingual Word Embeddings and a Monogamy Objective
This addresses a bottleneck in machine translation for low-resource languages, but it is incremental as it builds on existing cross-lingual embedding methods.
The paper tackles the problem of word alignment on very small parallel corpora by introducing an unsupervised objective to adapt cross-lingual word embeddings, outperforming fast-align on datasets of 25 to 500 sentences.
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.