`Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory

arXiv:2402.10643v1 Announce Type: new
Abstract: Extractive summaries are usually presented as lists of sentences with no expected cohesion between them. In this paper, we aim to enforce cohesion whilst controlling for informativeness and redundancy in summaries, in cases where the input exhibits high redundancy. The pipeline controls for redundancy in long inputs as it is consumed, and balances informativeness and cohesion during sentence selection. Our sentence selector simulates human memory to keep track of topics --modeled as lexical chains--, enforcing …

abstract aim arxiv cases cs.ai cs.cl human lists memory paper pipeline redundancy them together type