@article{Fu_Xian_Geng_Ge_Wang_Dong_Wang_de Melo_2020, title={ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/6279}, DOI={10.1609/aaai.v34i05.6279}, abstractNote={<p>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. The experiments show that our method outperforms several technically more powerful approaches, especially under challenging low-resource circumstances. The source code is available from https://github.com/zuohuif/ABSent along with relevant datasets.</p>}, number={05}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Fu, Zuohui and Xian, Yikun and Geng, Shijie and Ge, Yingqiang and Wang, Yuting and Dong, Xin and Wang, Guang and de Melo, Gerard}, year={2020}, month={Apr.}, pages={7756-7763} }