Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
Not on the map. Why?
Abstract (arXiv)
We present a novel technique for zero-shot paraphrase generation. The key contribution is an end-to-end multilingual paraphrasing model that is trained using translated parallel corpora to generate paraphrases into "meaning spaces" -- replacing the final softmax layer with word embeddings. This architectural modification, plus a training procedure that incorporates an autoencoding objective, enables effective parameter sharing across languages for more fluent monolingual rewriting, and facilitates fluency and diversity in generation. Our continuous-output paraphrase generation models outperform zero-shot paraphrasing baselines when evaluated on two languages using a battery of computational metrics as well as in human assessment.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 53 references that are in the map. First posted on arXiv 25 Oct 2021.
Builds on
23 of 53 references.
References · 23
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
- 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
- 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
- 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 272
- 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
- 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
- 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
- 2018Sequence-to-Sequence Data Augmentation for Dialogue Language Understandingcited by 67
- 2017A Deep Generative Framework for Paraphrase Generationcited by 54
11 more
- 2016Neural Paraphrase Generation with Stacked Residual LSTM Networkscited by 52
- 2017ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translationscited by 44
- 2020Generalized Entropy Regularization or: There's Nothing Special about Label Smoothingcited by 40
- 2019ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translationcited by 38
- 2020Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversitycited by 35
- 2017Learning Paraphrastic Sentence Embeddings from Back-Translated Bitextcited by 27
- 2018Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputscited by 26
- 2019Unsupervised Paraphrasing without Translationcited by 19
- 2018A task in a suit and a tie: paraphrase generation with semantic augmentationcited by 15
- 2019Zero-Shot Paraphrase Generation with Multilingual Language Modelscited by 7
- 2018Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminatorcited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1.
2 papers.