Table 4 ROUGE results for EXABSUMExtractive and EXABSUMAbstractive on CNN dataset while analyzing their features, Comb denotes the combination of the selected scoring techniques
From: EXABSUM: a new text summarization approach for generating extractive and abstractive summaries
Summary type | Scoring techniques | CNN | |
|---|---|---|---|
ROUGE-1 | ROUGE-2 | ||
EXABSUMExtractive | \(TR-ISF\) ONLY | 0.519 | 0.351 |
EXABSUMExtractive | Comb1: \(TR-ISF\)+ Sentence position | 0.541 | 0.379 |
EXABSUMExtractive | Comb2: \(TR-ISF\)+ Sentence Position + Sentence Length | 0.592 | 0.434 |
EXABSUMExtractive | Comb3:\(TR-ISF\)+ Sentence Position + Sentence Length + Sentence resemblance To the Title | 0.601 | 0.451 |
EXABSUMAbstractive | Graphs + Reranking based on keyphrases | 0.501 | 0.332 |