# Scalable Cross-Lingual Transfer of Neural Sentence Embeddings

## TL;DR

This paper explores scalable methods for aligning neural sentence embeddings across languages, demonstrating that representation transfer outperforms joint models especially with limited parallel data.

## Contribution

It introduces and compares three cross-lingual alignment frameworks, highlighting representation transfer as the most effective scalable approach.

## Key findings

- Representation transfer yields better alignment performance.
- Smaller parallel data sets are sufficient for effective transfer.
- Representation transfer outperforms joint modeling in evaluations.

## Abstract

We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment frameworks applied to these models: joint modeling, representation transfer learning, and sentence mapping, using parallel text to guide the alignment. Our results support representation transfer as a scalable approach for modular cross-lingual alignment of neural sentence embeddings, where we observe better performance compared to joint models in intrinsic and extrinsic evaluations, particularly with smaller sets of parallel data.