Hierarchical Mapping for Cross-lingual Word Embedding Alignment

Ion Madrazo Azpiazu, Maria Soledad Pera


The alignment of word embedding spaces in different languages into a common cross-lingual space has recently been in vogue. Strategies that do so compute pairwise alignments and then map multiple languages to a single pivot language (most often English). These strategies, however, are biased towards the choice of the pivot language, given that language proximity and the linguistic characteristics of the target language can strongly impact the resultant cross-lingual space in detriment of topologically distant languages. We present a strategy that eliminates the need for a pivot language by learning the mappings across languages in a hierarchical way. Experiments demonstrate that our strategy significantly improves vocabulary induction scores in all existing benchmarks, as well as in a new non-English centered benchmark we built, which we make publicly available.


  • There are currently no refbacks.

Copyright (c) 2020 Association for Computational Linguistics

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.