Unsupervised Learning Summarization Templates from Concise Summaries
We here present and compare two unsupervised approaches for inducing the main
conceptual information in rather stereotypical summaries in two different
We evaluate the two approaches in two different information extraction
settings: monolingual and cross-lingual information extraction.
The extraction systems are trained on auto-annotated summaries
(containing the induced concepts) and evaluated on human-annotated
documents. Extraction results are promising, being close in performance to
those achieved when the system is trained on human-annotated summaries.
Back to Papers Accepted