Finding relevant features for Korean comparative sentence extraction

In this paper, we study how to extract comparative sentences from Korean text documents. We decompose our task into three steps: (1) collecting comparative keywords; (2) extracting comparative-sentence candidates by keyword searching; and (3) eliminating non-comparative sentences from these candidates using machine learning techniques. We perform various experiments to find relevant features. As a result, our experiments show significant performance, an F1-score of 90.23%.

Research highlights
► This is the first research on an automatic comparison analysis in Korean.
► The proposed system extracts comparative sentences from Korean text documents.
► We collects comparative keywords and extracts comparative-sentence candidates by keyword searching.
► Non-comparative sentences are eliminated from the candidates using machine learning techniques.
► The proposed system showed a high performance, an F1-score of 90.23%.