COLING 2022 Shared Task: LED Finteuning and Recursive Summary Generation for Automatic Summarization of Chapters from Novels
Proceedings of The Workshop on Automatic Summarization for Creative Writing
We present the results of the Workshop on Automatic Summarization for Creative Writing 2022 Shared Task on summarization of chapters from novels. In this task, we finetune a pretrained transformer model for long documents called LongformerEncoderDecoder which supports seq2seq tasks for long inputs which can be up to 16k tokens in length. We use the Booksum dataset for longform narrative summarization for training and validation, which maps chapters from novels, plays and stories to highly abstractive human written summaries. We use a summary of summaries approach to generate the final summaries for the blind test set, in which we recursively divide the text into paragraphs, summarize them, concatenate all resultant summaries and repeat this process until either a specified summary length is reached or there is no significant change in summary length in consecutive iterations. Our best model achieves a ROUGE-1 F-1 score of 29.75, a ROUGE-2 F-1 score of 7.89 and a BERT F-1 score of 54.10 on the shared task blind test dataset.