Question Answering Summarization of Multiple Biomedical Documents
Z. Shi, G. Melli, Y. Wang, Y. Liu, B. Gu, M. Kashani, A. Sarkar, and F. Popowich. Proceedings of the 20th conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence, page 284-295. Springer, (2007)
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 abstracts as expert-written summaries. Evaluation results indicate that our system does help in answering questions and the automatically generated summaries are comparable to abstracts of biomedical articles, as evaluated using the ROUGE measure.
%0 Conference Paper
%1 Shi:2007
%A Shi, Zhongmin
%A Melli, Gabor
%A Wang, Yang
%A Liu, Yudong
%A Gu, Baohua
%A Kashani, Mehdi M.
%A Sarkar, Anoop
%A Popowich, Fred
%B Proceedings of the 20th conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence
%D 2007
%I Springer
%K question_answeringsummarisationbiomedical
%P 284-295
%T Question Answering Summarization of Multiple Biomedical Documents
%X 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 abstracts as expert-written summaries. Evaluation results indicate that our system does help in answering questions and the automatically generated summaries are comparable to abstracts of biomedical articles, as evaluated using the ROUGE measure.
@inproceedings{Shi:2007,
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 abstracts as expert-written summaries. Evaluation results indicate that our system does help in answering questions and the automatically generated summaries are comparable to abstracts of biomedical articles, as evaluated using the ROUGE measure.},
added-at = {2010-04-07T04:33:11.000+0200},
author = {Shi, Zhongmin and Melli, Gabor and Wang, Yang and Liu, Yudong and Gu, Baohua and Kashani, Mehdi M. and Sarkar, Anoop and Popowich, Fred},
biburl = {https://www.bibsonomy.org/bibtex/280af9bce243a8a6e5df7fca12ac125fe/diego_ma},
booktitle = {Proceedings of the 20th conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence},
citeseerurl = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.90.6578},
interhash = {9c133b7e40dc68e4186c14f222b60f6f},
intrahash = {80af9bce243a8a6e5df7fca12ac125fe},
keywords = {question_answeringsummarisationbiomedical},
pages = {284-295},
publisher = {Springer},
timestamp = {2010-04-07T04:33:11.000+0200},
title = {Question Answering Summarization of Multiple Biomedical Documents},
year = 2007
}