Assessment of text coherence using an ontology‐based relatedness measurement method

Abstract

This paper proposes a novel method for assessing text coherence. Central to this approach is an ontology‐based representation of text, which captures the level of relatedness between consecutive sentences via ontologies. Our method encompasses annotating text using ontological concepts and assessing text coherence based on relatedness measurement among these concepts. The ontology‐based relatedness measurement method used in this study considers various types of relationships in ontologies and derived relationships via an inference engine for computing relatedness. We hypothesized that rich variety of relationships and inferred facts in ontologies would improve the success of text coherence assessment. Our results demonstrate that the use of ontologies yields to coherence values that have a higher correlation with human ratings.

ANALISIS KOHERENSI DALAM TOPIK FIKSI MINI (Coherence Analysis in The Topic of Mini-Fiction)

“…Koherensi mengacu pada sarana ekspresif yang membangun wacana secara keseluruhan. Secara umum, koherensi adalah keterpaduan dan pemahaman semantik dalam menginterpretasi wacana secara implisit (Brown & Yule, 1983;Renkema, 2004;Keraf, 2005;Mulyana, 2005;Giray & Ünalır, 2019). Ada banyak sudut pandang yang bisa diterapkan dalam menganalisis wacana, yaitu: struktur wacana, fungsi wacana komunikatif, analisis tindak tutur, yang sering disebut dengan hubungan wacana pragmatis, subkreativitas wacana, dan kesimpulan yang dapat ditarik dari segmen wacana (Zikánová et al, 2015).…”