ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs
Computation and Language
2020-01-31 v1 Machine Learning
Abstract
A number of cross-lingual transfer learning approaches based on neural networks have been proposed for the case when large amounts of parallel text are at our disposal. However, in many real-world settings, the size of parallel annotated training data is restricted. Additionally, prior cross-lingual mapping research has mainly focused on the word level. This raises the question of whether such techniques can also be applied to effortlessly obtain cross-lingually aligned sentence representations. To this end, we propose an Adversarial Bi-directional Sentence Embedding Mapping (ABSent) framework, which learns mappings of cross-lingual sentence representations from limited quantities of parallel data.
Cite
@article{arxiv.2001.11121,
title = {ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs},
author = {Zuohui Fu and Yikun Xian and Shijie Geng and Yingqiang Ge and Yuting Wang and Xin Dong and Guang Wang and Gerard de Melo},
journal= {arXiv preprint arXiv:2001.11121},
year = {2020}
}