Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain
Jackie Chi Kit Cheung and Gerald Penn
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
In automatic summarization, centrality is the notion that a summary should contain the core parts of the source text. Current systems use centrality, along with redundancy avoidance and some sentence compression, to produce mostly extractive summaries. In this paper, we investigate how summarization can advance past this paradigm towards robust abstraction by making greater use of the domain of the source text. We conduct a series of studies comparing human-written model summaries to system summaries at the semantic level of caseframes. We show that model summaries (1) are more abstractive and make use of more sentence aggregation, (2) do not contain as many topical caseframes as system summaries, and (3) cannot be reconstructed solely from the source text, but can be if texts from in-domain documents are added. These results suggest that substantial improvements are unlikely to result from better optimizing centrality-based criteria, but rather more domain knowledge is needed.
Conference Manager (V2.61.0 - Rev. 2792M)