A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders
Abstract
Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the presence of specific linguistic properties, it is unclear whether the vector representations can be manipulated to indirectly steer such properties. For efficient learning, we investigate the use of a geometric mapping in embedding space to transform linguistic properties, without any tuning of the pre-trained sentence encoder or decoder. We validate our approach on three linguistic properties using a pre-trained multilingual autoencoder and analyze the results in both monolingual and cross-lingual settings.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2021
- DOI:
- 10.48550/arXiv.2104.03630
- arXiv:
- arXiv:2104.03630
- Bibcode:
- 2021arXiv210403630D
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Machine Learning
- E-Print:
- EMNLP 2021 - Short Paper Track