# Neural Network-based Word Alignment through Score Aggregation

arXiv: https://arxiv.org/abs/1606.09560 · HTML: https://mlsanity.com/paper/1606.09560/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2016.

## Built on by (most cited first, 3 of 3)

- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning](https://mlsanity.com/paper/2102.04009/) (2021)
- [BERT Cannot Align Characters](https://mlsanity.com/paper/2109.09700/) (2021)

## Abstract (arXiv)

We present a simple neural network for word alignment that builds source and target word window representations to compute alignment scores for sentence pairs. To enable unsupervised training, we use an aggregation operation that summarizes the alignment scores for a given target word. A soft-margin objective increases scores for true target words while decreasing scores for target words that are not present. Compared to the popular Fast Align model, our approach improves alignment accuracy by 7 AER on English-Czech, by 6 AER on Romanian-English and by 1.7 AER on English-French alignment.