Comparing Unsupervised Word Translation Methods Step by Step
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Comparing Unsupervised Word Translation Methods Step by Step. / Hartmann, Mareike ; Kementchedjhieva, Yova Radoslavova; Søgaard, Anders.
Advances in Neural Information Processing Systems 32 (NIPS 2019). 2019.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Comparing Unsupervised Word Translation Methods Step by Step
AU - Hartmann, Mareike
AU - Kementchedjhieva, Yova Radoslavova
AU - Søgaard, Anders
PY - 2019
Y1 - 2019
N2 - Cross-lingual word vector space alignment is the task of mapping the vocabularies of two languages into a shared semantic space, which can be used for dictionary induction, unsupervised machine translation, and transfer learning. In the unsupervised regime, an initial seed dictionary is learned in the absence of any known correspondences between words, through {\bf distribution matching}, and the seed dictionary is then used to supervise the induction of the final alignment in what is typically referred to as a (possibly iterative) {\bf refinement} step. We focus on the first step and compare distribution matching techniques in the context of language pairs for which mixed training stability and evaluation scores have been reported. We show that, surprisingly, when looking at this initial step in isolation, vanilla GANs are superior to more recent methods, both in terms of precision and robustness. The improvements reported by more recent methods thus stem from the refinement techniques, and we show that we can obtain state-of-the-art performance combining vanilla GANs with such refinement techniques.
AB - Cross-lingual word vector space alignment is the task of mapping the vocabularies of two languages into a shared semantic space, which can be used for dictionary induction, unsupervised machine translation, and transfer learning. In the unsupervised regime, an initial seed dictionary is learned in the absence of any known correspondences between words, through {\bf distribution matching}, and the seed dictionary is then used to supervise the induction of the final alignment in what is typically referred to as a (possibly iterative) {\bf refinement} step. We focus on the first step and compare distribution matching techniques in the context of language pairs for which mixed training stability and evaluation scores have been reported. We show that, surprisingly, when looking at this initial step in isolation, vanilla GANs are superior to more recent methods, both in terms of precision and robustness. The improvements reported by more recent methods thus stem from the refinement techniques, and we show that we can obtain state-of-the-art performance combining vanilla GANs with such refinement techniques.
M3 - Article in proceedings
BT - Advances in Neural Information Processing Systems 32 (NIPS 2019)
T2 - 33rd Conference on Neural Information Processing Systems (NeurIPS 2019)
Y2 - 8 December 2019 through 14 December 2019
ER -
ID: 240315759