L1-Refinement
Paddle implementation for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021)
Tested environment
- python==3.7.6
- scipy==1.4.1
- numpy==1.18.1
- paddle==2.1.0
- Intel Core i9-9900K CPU with 32GB Memory
Example command
python refiner.py --src_lang en --tgt_lang de --src_emb aligned/en-de/embeddings/en.vec --tgt_emb aligned/en-de/embeddings/de.vec --exp_path a/target/dir
About
If you like our project or find it useful, please give us a
@inproceedings{L1-Refinement,
title = "Cross-Lingual Word Embedding Refinement by $\ell_{1}$ Norm Optimisation",
author = "Peng, Xutan and
Lin, Chenghua and
Stevenson, Mark",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2021.naacl-main.214",
pages = "2690--2701"
}