• Corpus ID: 3470398

Word Translation Without Parallel Data

@article{Conneau2018WordTW,
  title={Word Translation Without Parallel Data},
  author={Alexis Conneau and Guillaume Lample and Marc'Aurelio Ranzato and Ludovic Denoyer and Herv'e J'egou},
  journal={ArXiv},
  year={2018},
  volume={abs/1710.04087}
}
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… 
Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora
TLDR
The model outperforms existing methods on bilingual lexicon induction and word alignment tasks and demonstrates that an encoder-decoder translation model is beneficial for learning cross-lingual representations, even in extremely low-resource scenarios.
Cross-Lingual Word Embeddings for Turkic Languages
TLDR
This paper presents the first viability study of established techniques to align monolingual embedding spaces for Turkish, Uzbek, Azeri, Kazakh and Kyrgyz, members of the Turkic family which is heavily affected by the low-resource constraint.
Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora
TLDR
This work proposes a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus based on an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence.
On the Robustness of Unsupervised and Semi-supervised Cross-lingual Word Embedding Learning
TLDR
An extensive evaluation over multiple cross-lingual embedding models, analyzing their strengths and limitations with respect to different variables such as target language, training corpora and amount of supervision puts in doubt the view that high-quality cross-lingsual embeddings can always be learned without much supervision.
Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences
In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary. Motivated by the ability of a
Phrase-Based & Neural Unsupervised Machine Translation
TLDR
This work investigates how to learn to translate when having access to only large monolingual corpora in each language, and proposes two model variants, a neural and a phrase-based model, which are significantly better than methods from the literature, while being simpler and having fewer hyper-parameters.
Unsupervised Machine Translation Using Monolingual Corpora Only
TLDR
This work proposes a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space and effectively learns to translate without using any labeled data.
UNSUPERVISED MACHINE TRANSLATION USING MONOLINGUAL CORPORA ONLY
  • Piotr
  • Computer Science
  • 2017
TLDR
This work proposes a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space and effectively learns to translate without using any labeled data.
Unsupervised Cross-lingual Word Embeddings Based on Subword Alignment
TLDR
Experimental results indicate that cross-lingual word embeddings obtained with the proposed unsupervised method were more accurate than those obtained by the state-of-the-art method, especially on distant language pairs.
Unsupervised Cross-lingual Transfer of Word Embedding Spaces
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Learning bilingual word embeddings with (almost) no bilingual data
TLDR
This work further reduces the need of bilingual resources using a very simple self-learning approach that can be combined with any dictionary-based mapping technique, and works with as little bilingual evidence as a 25 word dictionary or even an automatically generated list of numerals.
A Distribution-based Model to Learn Bilingual Word Embeddings
TLDR
A distribution based model to learn bilingual word embeddings from monolingual data is introduced and a novel cross-lingual learning objective is proposed which directly matches the distributions of wordembeddings in one language with that in the other language.
BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
TLDR
It is shown that bilingual embeddings learned using the proposed BilBOWA model outperform state-of-the-art methods on a cross-lingual document classification task as well as a lexical translation task on WMT11 data.
Supervised Bilingual Lexicon Induction with Multiple Monolingual Signals
TLDR
This work shows that only a few hundred translation pairs are needed to achieve strong performance on the bilingual lexicon induction task, and their approach yields an average relative gain in accuracy of nearly 50% over an unsupervised baseline.
Bilingual Word Embeddings from Non-Parallel Document-Aligned Data Applied to Bilingual Lexicon Induction
TLDR
It is shown that the BWE-based BLI models significantly outperform the MuPTM-based and context-counting models in this setting, and obtain the best reported BLI results for all three tested language pairs.
Adversarial Training for Unsupervised Bilingual Lexicon Induction
TLDR
This work shows that cross-lingual connection can actually be established without any form of supervision, by formulating the problem as a natural adversarial game, and investigating techniques that are crucial to successful training.
Offline bilingual word vectors, orthogonal transformations and the inverted softmax
TLDR
It is proved that the linear transformation between two spaces should be orthogonal, and this transformation can be obtained using the singular value decomposition.
Learning Crosslingual Word Embeddings without Bilingual Corpora
TLDR
This method takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages to achieve state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive results on the Monolingual word similarity and cross-lingual document classification task.
Compiling Bilingual Lexicon Entries From a Non-Parallel English-Chinese Corpus
TLDR
A novel context heterogeneity similarity measure between words and their translations in helping to compile bilingual lexicon entries from a non-parallel English-Chinese corpus is proposed and it is suggested that words with productive context in one language translate to words withproductive context in another language.
Exploiting Similarities among Languages for Machine Translation
TLDR
This method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data and uses distributed representation of words and learns a linear mapping between vector spaces of languages.
...
1
2
3
4
5
...