A Survey on Retrieval-Augmented Text Generation
It provides a comprehensive review for researchers in computational linguistics, but is incremental as a survey paper.
This paper surveys retrieval-augmented text generation, highlighting its advantages over conventional models and its state-of-the-art performance in various NLP tasks.
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and particularly has achieved state-of-the-art performance in many NLP tasks. This paper aims to conduct a survey about retrieval-augmented text generation. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks including dialogue response generation, machine translation, and other generation tasks. Finally, it points out some important directions on top of recent methods to facilitate future research.