Towards Coherent Multi-Document Summarization
Janara Christensen, Mausam Mausam, Stephen Soderland and Oren Etzioni
This paper presents G-FLOW, a novel system for coherent extractive
multi-document summarization (MDS). Where previous work on MDS considered
sentence selection and ordering separately, G-FLOW introduces a joint model for
selection and ordering that balances coherence and salience. G-FLOWâ€™s core
representation is a graph that approximates the discourse relations across
sentences based on indicators including discourse cues, deverbal nouns,
co-reference, and more. This graph enables G-FLOW to estimate the coherence of
a candidate summary.
We evaluate G-FLOW on Mechanical Turk, and find that it generates dramatically
better summaries than an extractive summarizer based on a pipeline of
state-of-the-art sentence selection and reordering components, underscoring the
value of our joint model.
Back to Papers Accepted