Abstract | ||
---|---|---|
RALI developed the system NESS2 for the TAC 2009 summarization task, with the main goal of testing the hypothesis that performing sentence selection in 2 steps improves the quality of the created sum- maries. The first step selects a number of top sentences, while the second step selects the best combination of the top scored sentences. We use the same small number of linguistic criteria to perform both evaluation steps. The two runs of NESS2, run IDs 8 and 10, ranked well in the competition, especially in linguis- tic quality and overall responsiveness, and the results show that the second step of sentence selection improves the perfor- mance of the system. |
Year | Venue | Field |
---|---|---|
2009 | TAC | Automatic summarization,Ranking,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Sentence |
DocType | Citations | PageRank |
Conference | 3 | 0.55 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pierre-Etienne Genest | 1 | 66 | 4.34 |
Guy Lapalme | 2 | 1420 | 105.55 |
luka nerima | 3 | 82 | 11.43 |
eric wehrli | 4 | 29 | 6.20 |