Non-Adversarial Unsupervised Word Translation
arXiv:1801.06126
Abstract
Unsupervised word translation from non-parallel inter-lingual corpora has attracted much research interest. Very recently, neural network methods trained with adversarial loss functions achieved high accuracy on this task. Despite the impressive success of the recent techniques, they suffer from the typical drawbacks of generative adversarial models: sensitivity to hyper-parameters, long training time and lack of interpretability. In this paper, we make the observation that two sufficiently similar distributions can be aligned correctly with iterative matching methods. We present a novel method that first aligns the second moment of the word distributions of the two languages and then iteratively refines the alignment. Extensive experiments on word translation of European and Non-European languages show that our method achieves better performance than recent state-of-the-art deep adversarial approaches and is competitive with the supervised baseline. It is also efficient, easy to parallelize on CPU and interpretable.
EMNLP 2018
References in corpus (5)
Cited by in corpus (9)
- One-Shot Unsupervised Cross Domain Translation
- Unsupervised Hyperalignment for Multilingual Word Embeddings
- Unsupervised Alignment of Embeddings with Wasserstein Procrustes
- Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion
- On the Robustness of Unsupervised and Semi-supervised Cross-lingual Word Embedding Learning
- Robust Cross-lingual Embeddings from Parallel Sentences
- Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
- Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction
- Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval