A Survey on Retrieval-Augmented Text Generation

by   Huayang Li, et al.
University of Cambridge
Nara Institute of Science and Technology

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.


page 1

page 2

page 3

page 4


Data Augmentation for Text Generation Without Any Augmented Data

Data augmentation is an effective way to improve the performance of many...

SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation

Is it possible to leverage large scale raw and raw parallel corpora to b...

FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation

Retrieval-augmented generation models offer many benefits over standalon...

Text Infilling

Recent years have seen remarkable progress of text generation in differe...

Cognitive Mirage: A Review of Hallucinations in Large Language Models

As large language models continue to develop in the field of AI, text ge...

Retrieving Multimodal Information for Augmented Generation: A Survey

In this survey, we review methods that retrieve multimodal knowledge to ...

A Theoretical Analysis of the Repetition Problem in Text Generation

Text generation tasks, including translation, summarization, language mo...

Please sign up or login with your details

Forgot password? Click here to reset