Simple and Effective Paraphrastic Similarity from Parallel Translations

Abstract

We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating paraphrase corpora. Further, we show that the resulting model can be applied to cross-lingual tasks where it both outperforms and is orders of magnitude faster than more complex state-of-the-art baselines.

arXiv commentPublished as a short paper at ACL 2019

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
• Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
• An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification
• Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
• Filtering and Mining Parallel Data in a Joint Multilingual Space

Cited by in corpus (2)

• Self-training Improves Pre-training for Natural Language Understanding
• Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models