Discourse Structures to Reduce Discourse Incoherence in Blog Summarization
Shamima Mithun, Leila Kosseim · 2011
Discourse incoherence is an important and typical problem with multi-document extractive summaries. To address this issue, we have developed a schema-based summarization approach for query-based blog summaries that utilizes discourse structures. In our schema design, we tried to model discourse structures which are typically used by humans in their summary writing in response to a particular question type. In our approach, a sentence instantiates a specific slot of the schema based on its discourse structures. To validate our approach, we have built a system named BlogSum and have evaluated its performance through 4 human participants using a likert scale of 1 to 5. The evaluation results show that our approach has significantly improved summary coherence compared to the summaries with no discourse structuring without compromising on content evaluation. 1