`Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory
This work addresses the issue of disjointed summaries for users needing coherent text extraction, though it is incremental as it builds on existing extractive methods.
The paper tackled the problem of generating extractive summaries that lack cohesion by simulating human memory to enforce cohesive ties between sentences, achieving summaries that are as informative as those focusing only on informativeness or redundancy across various domains.
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 cohesive ties between noun phrases. Across a variety of domains, our experiments revealed that it is possible to extract highly cohesive summaries that nevertheless read as informative to humans as summaries extracted by only accounting for informativeness or redundancy. The extracted summaries exhibit smooth topic transitions between sentences as signaled by lexical chains, with chains spanning adjacent or near-adjacent sentences.