Chimp water wave optimisation enabled random multimodal deep learning for text summarisation

Text summarisation is the process of compressing longer documents into a shorter version without losing their overall information contents. However, automatic text summarisation is still a challenging issue due to the unavailability of the corpus. To overcome the issues, a robust summarisation model, named chimp water wave optimisation-based random multimodal deep learning (ChWWO-based RMDL) method is developed for text summarisation. Here, the bidirectional encoder representations from transformers (BERT) tokenisation is accomplished for performing the tokenisation operation. With the tokens, aspect term extraction (ATE) is done to improve the summarisation performance. The RMDL model is employed for the text summarisation process where the developed ChWWO algorithm is utilised for training the RMDL model. However, the devised ChWWO is the integration of the chimp optimisation algorithm (ChOA) and water wave optimisation (WWO). The developed method achieved superior performance with a higher precision of 0.961, recall of 0.971, and F-measure of 0.966, respectively.