Abstract
In abstract-like summarisation, extracted sentences containing key content are often
revised to improve the coherence of the overall summary. In this work, we consider the task of Global Revision, in which a key sentence is revised and supplemented
with additional content from the original document. Specifically, this task comprises two subtasks: selecting content; and grammatically ordering content,
the focus of this paper. Using statistical dependency models, we search for
a Maximal Spanning (Dependency) Tree that structures recycled words and phrases
to form a novel sentence. Combining a modified version of Prim’s algorithm with
a four-gram language model, we evaluated our system on a sentence regeneration task
obtaining Bleu scores of .30, a statistically significant improvement above the baseline.
Original language | English |
---|---|
Title of host publication | PACLING '07 |
Subtitle of host publication | proceedings of the conference Pacific Association for Computational Linguistics ; 19-21 September 2007 University of Melbourne, Melbourne, Australia |
Place of Publication | Melbourne, Australia |
Publisher | Pacific Association for Computational Linguistics |
Pages | 226-235 |
Number of pages | 10 |
Publication status | Published - 2007 |
Event | Conference of the Pacific Association for Computational Linguistics (10th : 2007) - Melbourne Duration: 19 Sep 2007 → 21 Sep 2007 |
Conference
Conference | Conference of the Pacific Association for Computational Linguistics (10th : 2007) |
---|---|
City | Melbourne |
Period | 19/09/07 → 21/09/07 |