FEATURE SELECTION AND CLASSIFICATION INTEGRATED METHOD FOR IDENTIFYING CITED TEXT SPANS FOR CITANCES ON IMBALANCED DATA

Recent studies in scientific paper summarization have explored a new form of structured summary for a reference paper by grouping all cited and citing sentences together by facet. This involves three main tasks: (1) identifying cited text spans for citances (i.e., citing sentences), (2) classifying their discourse facets, and (3) generating a structured summary from the cited text spans and citances. This paper focuses on the first task, and approaches the task as binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. We propose a new method that integrates feature selection and classification techniques to enhance classification performance. The proposed method investigates combinations of six feature selection methods (chi(2)-Statistics, Information Gain, Gain Ratio, Relief-F, Significance Attribute Evaluation, and Symmetrical Uncertainty), and five classification algorithms (k-Nearest Neighbors, Decision Tree, Support Vector Machine, Naive Bayes, and Random Forest). Additionally, to address imbalanced data during training, we apply SMOTE (Synthetic Minority Over sampling Technique) to introduce synthetic biases towards the minority. Experiments are conducted using the CLSciSumm corpora to compare the effect of feature selection applied to classification. The results reveal the benefits of feature selection in significantly boosting performance of F-1 score metric, and show that our method is competitive to the state-of-the-art methods in the CL-SciSumm evaluations.