An Improved Key Sentence Extraction Algorithm Based on Features Computing Oriented to Argumentative Essay

Because of the strong logical structure and narrative structure of argumentative essay, we propose an improved key sentence extraction algorithm based on features computing, which not only considers word level features, such as keywords attribute, sentiment attribute, verb attribute, conjunction attribute, summary word attribute and viewpoint word attribute, but also includes sentence level features, such as position attribute, sentence frequency attribute and title similarity attribute. In our algorithm, a scoring mechanism is set for text sentences according to above attributes extraction, then the top sentences are extracted as key sentences. Experiments show that it has good performance and proves the effectiveness of the key sentence extraction algorithm based on features computing.