Now showing items 33-36 of 319

    • Thumbnail

      Learning principled bilingual mappings of word embeddings while preserving monolingual invariance 

      Artetxe Zurutuza, Mikel; Labaka Intxauspe, Gorka ORCID; Agirre Bengoa, Eneko ORCID (2016)
      Mapping word embeddings of different languages into a single space has multiple applications. In order to map from a source space into a target space, a common approach is to learn a linear mapping that minimizes the ...
    • Thumbnail

      Learning bilingual word embeddings with (almost) no bilingual data 

      Artetxe Zurutuza, Mikel; Labaka Intxauspe, Gorka ORCID; Agirre Bengoa, Eneko ORCID (ACL, 2017)
      Most methods to learn bilingual word embeddings rely on large parallel corpora, which is difficult to obtain for most language pairs. This has motivated an active research line to relax this requirement, with methods that ...
    • Thumbnail

      A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings 

      Artetxe Zurutuza, Mikel; Labaka Intxauspe, Gorka ORCID; Agirre Bengoa, Eneko ORCID (ACL, 2018)
      Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable ...
    • Thumbnail

      Unsupervised Statistical Machine Translation 

      Artetxe Zurutuza, Mikel; Labaka Intxauspe, Gorka ORCID; Agirre Bengoa, Eneko ORCID (ACL, 2018)
      While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et ...