A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders
This addresses the challenge of efficiently controlling linguistic features in multilingual NLP systems, though it appears incremental as it builds on existing pre-trained models.
The paper tackled the problem of manipulating linguistic properties in sentence embeddings without retraining, using a geometric mapping in embedding space, and demonstrated its effectiveness on three linguistic properties in monolingual and cross-lingual settings.
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.