Word Translation Without Parallel Data

Abstract

State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.

ICLR 2018

References in corpus (1)

• Learning Crosslingual Word Embeddings without Bilingual Corpora

Cited by in corpus (12)

• Does Object Recognition Work for Everyone?
• XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering
• Integrating Social Media into a Pan-European Flood Awareness System: A Multilingual Approach
• Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input
• Crosslingual Document Embedding as Reduced-Rank Ridge Regression
• Deep Matching Autoencoders
• Cross-Lingual Transfer Learning for Question Answering
• Aligning Vector-spaces with Noisy Supervised Lexicons
• Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B
• SAR: Learning Cross-Language API Mappings with Little Knowledge
• Sentence transition matrix: An efficient approach that preserves sentence semantics
• Cross-lingual transfer learning for spoken language understanding