GLEANS: A Generator of Logical Extracts and Abstracts for Nice Summaries
Hal Daum, Abdessamad Echihabi, Daniel Marcu, Dragos Stefan Munteanu, Radu Soricut · 2002
We describe GLEANS, a summarization system that uses four novel techniques for summarizating document collections. (i) GLEANS first maps all documents in a collection into a canonical, database-like representation that makes explicit the main entities and relations in a document collection. (ii) GLEANS also classifies each document collection into one of four categories: collections about a single person, single event, multiple event, and natural disaster. (iii) For each type of document collection, GLEANS generates a short headline using a set of predefined templates. For multi-event documents, GLEANS also generates from scratch, using predefined templates, the first two sentences in the abstract. (iv) The rest of the summary is then generated by extracting from the database sentences that conform to a set of predefined schemas and by presenting them in an order that reflects coherence constraints specific to each collection category.