Cross-lingual language tasks typically require a substantial amount of annotated data or parallel translation data. We explore whether language representations that capture relationships among languages can be learned and subsequently leveraged in cross-lingual tasks without the use of parallel data. We generate dense embeddings for 29 languages using a denoising autoencoder, and evaluate the embeddings using the World Atlas of Language Structures (WALS) and two extrinsic tasks in a zero-shot setting: cross-lingual dependency parsing and cross-lingual natural language inference.
@article{arxiv.2106.02082,
title = {Language Embeddings for Typology and Cross-lingual Transfer Learning},
author = {Dian Yu and Taiqi He and Kenji Sagae},
journal= {arXiv preprint arXiv:2106.02082},
year = {2021}
}