ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs
arXiv:2001.11121
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.
References in corpus (6)
- Conditional Generative Adversarial Nets
- Exploiting Similarities among Languages for Machine Translation
- Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
- Multilingual Neural Machine Translation With Soft Decoupled Encoding
- Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax
- OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization