Paraphrase Generation: A Survey of the State of the Art

By Jianing Zhou, Suma Bhat. 2021

92 citations recorded by the source corpus.

This paper focuses on paraphrase generation,which is a widely studied natural language generation task in NLP. With the development of neural models, paraphrase generation research has exhibited a gradual shift to neural methods in the recent years. This has provided architectures for contextualized representation of an input text and generating fluent, diverseand human-like paraphrases. This paper surveys various approaches to paraphrase generation with a main focus on neural methods.

Subfields: Natural Language Processing, Natural Language Generation

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

1. Jason Baldridge
2. Yonghui Wu
3. Michael Bendersky
4. Yinfei Yang
5. Wei Han
6. Burcu Karagol Ayan
7. Jiahui Yu
8. Thang Luong

In Natural Language Generation

1. Jason Baldridge
2. Michael Bendersky
3. Alireza Salemi
4. Hamed Zamani
5. Yonghui Wu
6. Sheshera Mysore

Citations in the corpus

• Scaling Autoregressive Models for Content-Rich Text-to-Image Generation (2022, methodology): “Parti uses an architecture and strategy that is directly connected to the neural sequence-to-sequence models used for machine translation [94] and other communication aids such as sentence simplification [95] and paraphrasing [96].”
• LaMP: When Large Language Models Meet Personalization (2023, methodology): “Following previous works (Zhou and Bhat, 2021; Panthaplackel et al., 2022), we use Rouge-1/Rouge-L (Lin, 2004) as evaluation metrics for generation tasks (LaMP-4 to 7).”