An Entity-Driven Framework for Abstractive Summarization
This addresses the issue of generating coherent and faithful summaries for users relying on automated text summarization, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of incoherent and unfaithful outputs in abstractive summarization by introducing SENECA, an entity-driven framework that improves summary quality. The model significantly outperforms previous state-of-the-art on ROUGE and coherence measures on New York Times and CNN/Daily Mail datasets, with human judges rating its summaries as more informative and coherent.
Abstractive summarization systems aim to produce more coherent and concise summaries than their extractive counterparts. Popular neural models have achieved impressive results for single-document summarization, yet their outputs are often incoherent and unfaithful to the input. In this paper, we introduce SENECA, a novel System for ENtity-drivEn Coherent Abstractive summarization framework that leverages entity information to generate informative and coherent abstracts. Our framework takes a two-step approach: (1) an entity-aware content selection module first identifies salient sentences from the input, then (2) an abstract generation module conducts cross-sentence information compression and abstraction to generate the final summary, which is trained with rewards to promote coherence, conciseness, and clarity. The two components are further connected using reinforcement learning. Automatic evaluation shows that our model significantly outperforms previous state-of-the-art on ROUGE and our proposed coherence measures on New York Times and CNN/Daily Mail datasets. Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.