Bilingual Word Embeddings from Parallel and Non-parallel Corpora for Cross-Language Text Classification

By Aditya Mogadala, Achim Rettinger. 2016

89 citations recorded by the source corpus.

In many languages, sparse availability of resources causes numerous challenges for textual analysis tasks. Text classification is one of such standard tasks that is hindered due to limited availability of label information in lowresource languages. Transferring knowledge (i.e. label information) from high-resource to low-resource languages might improve text classification as compared to the other approaches like machine translation. We introduce BRAVE (Bilingual paRAgraph VEctors), a model to learn bilingual distributed representations (i.e. embeddings) of words without word alignments either from sentencealigned parallel or label-aligned non-parallel document corpora to support cross-language text classification. Empirical analysis shows that classification models trained with our bilingual embeddings outperforms other stateof-the-art systems on three different crosslanguage text classification tasks.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Learning bilingual word embeddings with (almost) no bilingual data (2017, methodology): “A possible relaxation is to use document-aligned or label-aligned comparable corpora (Søgaard et al., 2015; Vulić and Moens, 2016; Mogadala and Rettinger, 2016), but large amounts of such corpora are not always available for some language pairs.”
A Corpus for Multilingual Document Classification in Eight Languages (2018, background): “An extension to the transfer between English and French and Spanish respectively was proposed by (Mogadala and Rettinger, 2016).”
A Survey of Cross-lingual Word Embedding Models (2017, background): “Many mapping-based approaches propose to refine the mapping to improve the quality of the initial seed lexicon. Vulić and Korhonen (2016) propose to learn a first shared bilingual embedding space based on an existing cross-lingual embedding model.”
Learning Joint Multilingual Sentence Representations with Neural Machine Translation (2017, background): “, 2013) which trains bilingual autoencoders with the objective of minimizing reconstruction error between two languages, and BRAVE (Bilingual paRAgraph VEctors) (Mogadala and Rettinger, 2016) which learns both bilingual word embeddings and sentence embeddings from either sentence-aligned parallel co”