A Discriminative Neural Model for Cross-Lingual Word Alignment

We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model. In experiments based on a small number of labeled examples (similar to 1.7K-5K sentences) we evaluate its performance intrinsically on both English-Chinese and English-Arabic alignment, where we achieve major improvements over unsupervised baselines (11-27 F1). We evaluate the model extrinsically on data projection for Chinese NER, showing that our alignments lead to higher performance when used to project NER tags from English to Chinese. Finally, we perform an ablation analysis and an annotation experiment that jointly support the utility and feasibility of future manual alignment elicitation.