| Autor: |
Singh, Arwinder, Josan, Gurpreet Singh |
| Předmět: |
|
| Zdroj: |
International Journal of Next-Generation Computing; Mar2022, Vol. 13 Issue 1, p83-108, 26p |
| Abstrakt: |
Paraphrasing is an act of generating similar text to the source text with different expressions. Paraphrase generation is an important task in various Natural Language Processing applications such as machine translation, question-answering, information retrieval and sentence simplification. The advancements in deep learning improved paraphrase generation. So, the aim of this paper is to provide a review from RNN based approaches to current state-of-the-art models. The current paraphrase generation techniques are using basic seq2seq with attention, neural machine translation, deep generative models and reinforcement learning methodologies. A comprehensive study is presented based on the methodology used, strengths of the systems and datasets used in these approaches. The paper will help the readers to know the basics of paraphrasing concepts, their types, various applications of paraphrase generation and the current algorithms developed for generating paraphrases. The various datasets for paraphrasing models are also explored along with future directions for scholars and persons from industry in the proposed article. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
