English

Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron

Computation and Language 2019-06-06 v1 Machine Learning

Abstract

We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and target sentence embeddings to share the same space without the help of a pivot language or an additional transformation. We train a multilayer perceptron on top of the sentence embeddings to extract good bilingual sentence pairs from nonparallel or noisy parallel data. Our approach shows promising performance on sentence alignment recovery and the WMT 2018 parallel corpus filtering tasks with only a single model.

Keywords

Cite

@article{arxiv.1906.01942,
  title  = {Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron},
  author = {Yunsu Kim and Hendrik Rosendahl and Nick Rossenbach and Jan Rosendahl and Shahram Khadivi and Hermann Ney},
  journal= {arXiv preprint arXiv:1906.01942},
  year   = {2019}
}

Comments

ACL 2019 Repl4NLP camera-ready

R2 v1 2026-06-23T09:43:01.659Z