Multilingual Deep Learning

By Sarath Chandar. 2013

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

XNLI: Evaluating Cross-lingual Sentence Representations (2018, background): “For example, Chandar et al. (2013) train bilingual autoencoders with the objective of minimizing reconstruction error between two languages.”
Multilingual Distributed Representations without Word Alignment (2013, methodology): “[23] propose methods for learning word embeddings by exploiting bilingual data, not unlike the method proposed in this paper.”
Learning Joint Multilingual Sentence Representations with Neural Machine Translation (2017, background): “Other multilingual sentence representation learning techniques include BAE (Chandar et al., 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…”
A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images (2018, methodology): “been used to deal with other heterogeneous data [17], [51].”
Concatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations (2018, methodology): “Finally, Chandar et al. (2013) train a cross-lingual auto-encoder to learn representations that allow reconstructing sentences and documents in different languages, and Schwenk and Douze (2017) use representations learned by an NMT model for translation retrieval.”
Learning Bilingual Word Representations by Marginalizing Alignments (2014, methodology): “Other recent approaches include Sarath Chandar et al. (2013), Lauly et al. (2013) and Hermann and Blunsom (2014a, 2014b).”