# Graph Neural Networks for Multiparallel Word Alignment

arXiv: https://arxiv.org/abs/2203.08654 · HTML: https://mlsanity.com/paper/2203.08654/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 88 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [75 Languages, 1 Model: Parsing Universal Dependencies Universally](https://mlsanity.com/paper/1904.02099/) (2019)
- [Structured Neural Summarization](https://mlsanity.com/paper/1811.01824/) (2018)
- [Semantic Graphs for Generating Deep Questions](https://mlsanity.com/paper/2004.12704/) (2020)
- [Accurate Word Alignment Induction from Neural Machine Translation](https://mlsanity.com/paper/2004.14837/) (2020)
- [Axioms for Centrality](https://mlsanity.com/paper/1308.2140/) (2013)
- [Past, Present, Future: A Computational Investigation of the Typology of Tense in 1000 Languages](https://mlsanity.com/paper/1704.08914/) (2017)
- [A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments](https://mlsanity.com/paper/1608.05426/) (2016)
- [HELFI: a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment](https://mlsanity.com/paper/2003.07456/) (2020)
- [Graph Algorithms for Multiparallel Word Alignment](https://mlsanity.com/paper/2109.06283/) (2021)
- [ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus](https://mlsanity.com/paper/2107.06632/) (2021)

## Built on by (most cited first, 4 of 4)

- [Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging](https://mlsanity.com/paper/2210.09840/) (2022)
- [Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation](https://mlsanity.com/paper/2310.14806/) (2023)
- [The taggedPBC: Annotating a massive parallel corpus for crosslinguistic investigations](https://mlsanity.com/paper/2505.12560/) (2025)
- [UPRPRC: Unified Pipeline for Reproducing Parallel Resources -- Corpus from the United Nations](https://mlsanity.com/paper/2509.15789/) (2025)

## Abstract (arXiv)

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection, and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position, and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection provides valuable information for multiparallel word alignment. Our method outperforms previous work on three word-alignment datasets and on a downstream task.