GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarization
This work addresses the challenge of reliable evaluation for abstractive summarization across multiple genres, which is incremental as it builds on existing datasets and methods.
The authors tackled the problem of evaluating abstractive summarization across diverse genres by introducing GUMSum, a dataset with 12 written and spoken genres, and found that GPT-3 underperforms humans with varying quality across genres.
Automatic summarization with pre-trained language models has led to impressively fluent results, but is prone to 'hallucinations', low performance on non-news genres, and outputs which are not exactly summaries. Targeting ACL 2023's 'Reality Check' theme, we present GUMSum, a small but carefully crafted dataset of English summaries in 12 written and spoken genres for evaluation of abstractive summarization. Summaries are highly constrained, focusing on substitutive potential, factuality, and faithfulness. We present guidelines and evaluate human agreement as well as subjective judgments on recent system outputs, comparing general-domain untuned approaches, a fine-tuned one, and a prompt-based approach, to human performance. Results show that while GPT3 achieves impressive scores, it still underperforms humans, with varying quality across genres. Human judgments reveal different types of errors in supervised, prompted, and human-generated summaries, shedding light on the challenges of producing a good summary.