ChemDataWriter: a transformer-based toolkit for auto-generating books that summarise research

Since the number of scientific papers has grown substantially over recent years, scientists spend much time searching, screening, and reading papers to follow the latest research trends. With the development of advanced natural-language-processing (NLP) models, transformer-based text-generation algorithms have the potential to summarise scientific papers and automatically write a literature review from numerous scientific publications. In this paper, we introduce a Python-based toolkit, ChemDataWriter, which auto-generates books about research in a completely unsupervised fashion. ChemDataWriter adopts a conservative book-generation pipeline to automatically write the book by suggesting potential book content, retrieving and re-ranking the relevant papers, and then summarising and paraphrasing the text within the paper. To the best of our knowledge, ChemDataWriter is the first open-source toolkit in the area of chemistry to be able to compose a literature review entirely via artificial intelligence once one has suggested a broad topic. We also provide an example of a book that ChemDataWriter has auto-generated about battery-materials research. To aid the use of ChemDataWriter, its code is provided with associated documentation to serve as a user guide. ChemDataWriter automatically generates literature reviews via artificial intelligence that suggests potential book content, by retrieving and re-ranking relevant papers that the user has provided as input, and summarising and paraphrasing the text within these papers.