Unsupervised Multilingual Word Embeddings

08/27/2018
by   Xilun Chen, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/11/2017

ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge

This paper describes Luminoso's participation in SemEval 2017 Task 2, "M...
research
09/07/2018

Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models

We propose an unsupervised method to obtain cross-lingual embeddings wit...
research
02/21/2020

Refinement of Unsupervised Cross-Lingual Word Embeddings

Cross-lingual word embeddings aim to bridge the gap between high-resourc...
research
10/27/2020

Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora

We propose a new approach for learning contextualised cross-lingual word...
research
04/10/2020

A Simple Approach to Learning Unsupervised Multilingual Embeddings

Recent progress on unsupervised learning of cross-lingual embeddings in ...
research
01/19/2018

A Resource-Light Method for Cross-Lingual Semantic Textual Similarity

Recognizing semantically similar sentences or paragraphs across language...
research
02/03/2021

Bootstrapping Multilingual AMR with Contextual Word Alignments

We develop high performance multilingualAbstract Meaning Representation ...

Please sign up or login with your details

Forgot password? Click here to reset