| P12-1106 | state-of-the-art summarization systems are | extraction-based systems | , which do not generate new words |
| W09-1801 | valid alternative to existing | extraction-based systems | . However , it is worth noting |
| P99-1071 | methods used for evaluation of | extraction-based systems | are not applicable for a system |
| W00-1710 | development of an information | extraction-based system | for semi-automatic annotation |
| P10-1058 | it is a viable alternative to | extraction-based systems | . Both ROUGE scores and the results |
| P11-3014 | as well as summaries created by | extraction-based systems | and a baseline of selecting the |
| P13-1137 | than those of the utterance-level | extraction-based system | , preferring them over summaries |
| P13-1137 | a state-of-the-art supervised | extraction-based system | . Human evaluation also indicates |
| W03-1101 | the expected performance of an | extraction-based system | would be between 0.40 and 0.50 |
| P12-2069 | to improve the performance of | extraction-based systems | , like ( Barzilay and Lee , 2004 |
| P13-1137 | the state-of-the-art supervised | extraction-based systems | in both automatic and manual |
| N04-4001 | has assessed the potential for | extraction-based systems | when attempting to summarize |
| N04-4001 | they found that state-of-the-art | extraction-based systems | are still 15 % -24 % 2 away from |
| W03-1203 | , compared to those by another | extraction-based system | MEAD ( Radev 2002 ) , and against |
