Translation Inference through Multi-lingual Word Embedding Similarity

Kathrin Donandt, Christian Chiarcos
2019 Zenodo  
This paper describes our contribution to the Shared Task on Translation Inference across Dictionaries (TIAD-2019). In our approach, we construct a multi-lingual word embedding space by projecting new languages in the feature space of a language for which a pretrained embedding model exists. We use the similarity of the word embeddings to predict candidate translations. Even if our projection methodology is rather simplistic, our system outperforms the other participating systems with respect to
more » ... the F1 measure for the language pairs which we predicted.
doi:10.5281/zenodo.3555183 fatcat:ky5avcys7vd4lglkyuqw3fpvfi