Graph Algorithms for Multiparallel Word Alignment
This work addresses the limitation of existing word alignment algorithms that ignore multiparallel data, which is important for multilingual NLP applications like typological research and machine translation.
The authors tackled the problem of word alignment in multiparallel corpora by representing bilingual alignments as a graph and predicting additional edges using graph algorithms, resulting in absolute F1 improvements of up to 28% over baseline bilingual aligners.
With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts, and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario, and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit the multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements in $F_1$ of up to 28% over the baseline bilingual word aligner in different datasets.