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

By Mikel Artetxe, Gorka Labaka, Eneko Agirre. 2018

628 citations recorded by the source corpus.

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 conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution. Our method succeeds in all tested scenarios and obtains the best published results in standard datasets, even surpassing previous supervised systems. Our implementation is released as an open source project at https://github.com/artetxem/vecmap.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Graham Neubig
  2. Mohit Bansal
  3. Luke S. Zettlemoyer
  4. Jianfeng Gao
  5. Sebastian Ruder
  6. Kyunghyun Cho
  7. Percy Liang
  8. Yoshua Bengio

In Natural Language Processing

  1. Graham Neubig
  2. Sebastian Ruder
  3. Ivan Vulic
  4. Mohit Bansal
  5. Richard Socher
  6. Kyunghyun Cho
  7. Luke S. Zettlemoyer
  8. Hinrich Schütze

In Representation & Self-Supervised Learning

  1. Ivan Vulic
  2. Sebastian Ruder
  3. Graham Neubig
  4. Mohammad Taher Pilehvar
  5. Goran Glavas
  6. José Camacho-Collados
  7. Anders Søgaard
  8. Mikel Artetxe

In Machine Translation

  1. Ivan Vulic
  2. Sebastian Ruder
  3. Graham Neubig
  4. Mikel Artetxe
  5. Goran Glavas
  6. Eneko Agirre
  7. Gorka Labaka
  8. Anders Søgaard

Citations in the corpus