Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion
arXiv:1804.07745
Abstract
Continuous word representations learned separately on distinct languages can be aligned so that their words become comparable in a common space. Existing works typically solve a least-square regression problem to learn a rotation aligning a small bilingual lexicon, and use a retrieval criterion for inference. In this paper, we propose an unified formulation that directly optimizes a retrieval criterion in an end-to-end fashion. Our experiments on standard benchmarks show that our approach outperforms the state of the art on word translation, with the biggest improvements observed for distant language pairs such as English-Chinese.
References in corpus (6)
- Efficient Estimation of Word Representations in Vector Space
- Exploiting Similarities among Languages for Machine Translation
- Manopt, a Matlab toolbox for optimization on manifolds
- Word Translation Without Parallel Data
- Unsupervised Alignment of Embeddings with Wasserstein Procrustes
- Non-Adversarial Unsupervised Word Translation
Cited by in corpus (12)
- Unsupervised Hyperalignment for Multilingual Word Embeddings
- Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
- PidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to English
- Translating and Evolving: Towards a Model of Language Change in DisCoCat
- Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces
- A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
- Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
- Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry
- Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotation
- Cross-lingual hate speech detection based on multilingual domain-specific word embeddings
- SChME at SemEval-2020 Task 1: A Model Ensemble for Detecting Lexical Semantic Change
- Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce