Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

View Researcher's Other Codes

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Please contact us in case of a broken link from here

Download
Authors Tomas Mikolov, Piotr Bojanowski, Armand Joulin, Herve Jegou, Edouard Grave
Journal/Conference Name EMNLP 2018 10
Paper Category
Paper Abstract Continuous word representations learned separately on distinct languages can be aligned so that their words become comparable in a common space. Existing works typically solve a least-square regression problem to learn a rotation aligning a small bilingual lexicon, and use a retrieval criterion for inference. In this paper, we propose an unified formulation that directly optimizes a retrieval criterion in an end-to-end fashion. Our experiments on standard benchmarks show that our approach outperforms the state of the art on word translation, with the biggest improvements observed for distant language pairs such as English-Chinese.
Date of publication 2018
Code Programming Language Multiple
Comment

Copyright Researcher 2022