Fig. 2: Results of filtering valid papers and paragraphs.
From: Building an end-to-end battery recipe knowledge base via transformer-based text mining
a Two-dimensional map of topics, which was obtained by applying principal component analysis to a topic-keyword distribution matrix. Here, the node size is proportional to the ratio of each topic within the entire corpus. b, c Frequent keywords of ‘cathode materials synthesis’ and ‘cell assembly’ topics.
