Graph Algorithms for Multiparallel Word Alignment

Abstract

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 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 of F 1 of up to 28% over the baseline bilingual word aligner in different datasets.

Disambiguation in context in the Russian National Corpus: 20 yeas later

“…The discussion about data quality takes place within the common morphology tagging discourse (Muradoglu and Hulden, 2022). New methods are being developed, for instance, graph-based part-of-speech tagging (ImaniGooghari et al, 2022), or using compressed FastText models (Nevěřilová, 2022). Specifically concerning Russian, joined morphological analysis and morpheme segmentation models were proposed recently (Bolshakova and Sapin, 2022).…”