The Exploration of Knowledge-Preserving Prompts for Document Summarisation
It addresses factual consistency in summarization for NLP applications, but is incremental as it builds on existing prompt-tuning methods.
This study tackled factual inconsistencies in document summarization by exploring prompts to incorporate factual knowledge, resulting in ROUGE improvements that indicate boosted performance.
Despite the great development of document summarisation techniques nowadays, factual inconsistencies between the generated summaries and the original texts still occur from time to time. This study explores the possibility of adopting prompts to incorporate factual knowledge into generated summaries. We specifically study prefix-tuning that uses a set of trainable continuous prefix prompts together with discrete natural language prompts to aid summary generation. Experimental results demonstrate that the trainable prefixes can help the summarisation model extract information from discrete prompts precisely, thus generating knowledge-preserving summaries that are factually consistent with the discrete prompts. The ROUGE improvements of the generated summaries indicate that explicitly adding factual knowledge into the summarisation process could boost the overall performance, showing great potential for applying it to other natural language processing tasks.