paper-with-me

Papers

Unsupervised Multilingual Word Embeddings

2018-08-27 · EMNLP 2018 10 · Xilun Chen, Claire Cardie

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant advantage over traditional supervised approaches and opens many new possibilities for low-resource languages. Prior art for learning UMWEs, however, merely relies on a number of independently trained Unsupervised Bilingual Word Embeddings (UBWEs) to obtain multilingual embeddings. These methods fail to leverage the interdependencies that exist among many languages. To address this shortcoming, we propose a fully unsupervised framework for learning MWEs that directly exploits the relations between all language pairs. Our model substantially outperforms previous approaches in the experiments on multilingual word translation and cross-lingual word similarity. In addition, our model even beats supervised approaches trained with cross-lingual resources.

📄 PDF Abstract BibTeX arXiv:1808.08933

Code (3)

ccsasuke/umwe 공식 구현 pytorch
selimseker/logogram-language-generator pytorch
soumyaumass/umwe pytorch

Tasks

Multilingual Word EmbeddingsTranslationWord EmbeddingsWord SimilarityWord Translation

Similar Papers 제목 키워드 기반

Multilingual Word Embeddings using Multigraphs

2016-12-14 · Radu Soricut, Nan Ding

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervi…

Machine TranslationMultilingual Word EmbeddingsSemantic SimilaritySemantic Textual Similarity+2

Unsupervised Alignment of Embeddings with Wasserstein Procrustes

2018-05-29 · Edouard Grave, Armand Joulin, Quentin Berthet

A library for Multilingual Unsupervised or Supervised word Embeddings

Word Embeddings

Learning Unsupervised Multilingual Word Embeddings with Incremental Multilingual Hubs

2019-06-01 · NAACL 2019 6 · Geert Heyman, Bregt Verreet, Ivan Vuli{\'c}, Marie-Francine Moens

Recent research has discovered that a shared bilingual word embedding space can be induced by projecting monolingual word embedding spaces from two languages using a self-learning paradigm without any bilingual supervisi…

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsDependency ParsingDocument Classification+3

A Simple Approach to Learning Unsupervised Multilingual Embeddings

2020-04-10 · EMNLP 2020 11 · Pratik Jawanpuria, Mayank Meghwanshi, Bamdev Mishra

Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve…

Bilingual Lexicon InductionDependency ParsingDocument ClassificationWord Alignment+1

Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models

2019-07-01 · ACL 2019 7 · Takashi Wada, Tomoharu Iwata, Yuji Matsumoto

Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data. These methods aim to find a linear transformation …

Word AlignmentWord Embeddings