Fig 1.
Overall proposed methodology.
Table 1.
Statistics of dataset.
Table 2.
Summary of extracted features for supervised extractive summarization.
Table 3.
Statistical analysis of extractive features of sentences.
Table 4.
Scores of feature selecting algorithms.
Table 5.
ROUGE scores of supervised summaries (mean and standard deviation over multiple runs).
Table 6.
Optimal training parameters used for the proposed CNN+LSTM and CNN+GRU models.
Fig 2.
Comparing the results of different models.
Fig 3.
Comparison with state-of-the-art.