Considering Length Diversity in Retrieval-Augmented Summarization
This addresses a specific bottleneck in summarization for NLP researchers, offering incremental improvements in efficiency.
This study tackled the problem of retrieval-augmented summarization by examining the impact of exemplar summary lengths under constraints, proposing the DL-MMR algorithm to better control lengths and reduce computational costs. Results showed DL-MMR achieved memory savings of 781,513 times and computational cost reduction of 500,092 times while maintaining informativeness.
This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths under length constraints, not covered by previous work. We propose a Diverse Length-aware Maximal Marginal Relevance (DL-MMR) algorithm to better control summary lengths. This algorithm combines the query relevance with diverse target lengths in retrieval-augmented summarization. Unlike previous methods that necessitate exhaustive exemplar exemplar relevance comparisons using MMR, DL-MMR considers the exemplar target length as well and avoids comparing exemplars to each other, thereby reducing computational cost and conserving memory during the construction of an exemplar pool. Experimental results showed the effectiveness of DL-MMR, which considers length diversity, compared to the original MMR algorithm. DL-MMR additionally showed the effectiveness in memory saving of 781,513 times and computational cost reduction of 500,092 times, while maintaining the same level of informativeness.