Question Answering Summarization of Multiple Biomedical Documents

Abstract. In this paper we introduce a system that automatically summarizes multiple biomedical documents relevant to a question. The system extracts biomedical and general concepts by utilizing concept-level knowledge from domain-specific and domain-independent sources. Semantic role labeling, semantic subgraph-based sentence selection and automatic post-editing are involved in the process of finding the information need. Due to the absence of expert-written summaries of biomedical documents, we propose an approximate evaluation by taking MEDLINE s as expert-written summaries. Evaluation results indicate that our system does help in answering questions and the automatically genummaries are comparable to abstracts of biomedical articles, as evaluated using the ROUGE measure.

• Type: Conference
• Year: 2007
• Where: AI
• Authors: Zhongmin Shi, Gabor Melli, Yang Wang, Yudong Liu, Baohua Gu, Mehdi M. Kashani, Anoop Sarkar, Fred Popowich
• Keywords: AI 2007, Artificial Intelligence, Biomedical, Biomedical Documents, Multiple Biomedical Documents