Graph Neural Networks for Multiparallel Word Alignment. (arXiv:2203.08654v2 [cs.CL] UPDATED)

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. …

alignment arxiv graph graph neural networks networks neural networks