Answering clinical questions with role identification
BioMed '03 Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine - Volume 13
Developing an approach for why-question answering
EACL '06 Proceedings of the Eleventh Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
A hybrid approach for the extraction of semantic relations from MEDLINE abstracts
CICLing'11 Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part II
Medical entity recognition: a comparison of semantic and statistical methods
BioNLP '11 Proceedings of BioNLP 2011 Workshop
| Hi-index | 0.00 |
Designing question answering systems requires efficient and deep analysis of natural language questions. A key process for this task is to translate the semantic relations expressed in the question into a machine-readable representation. In this paper we tackle question analysis in the medical field. More precisely, we study how to translate a natural language question into a machine-readable representation. The underlying transformation process requires determining three key points: (i) What are the main characteristics of medical questions? (ii) Which methods are the most fitted for the extraction of these characteristics? and (iii) how to translate the extracted information into a machine-understandable representation? We present a complete question analysis approach including medical entity recognition, semantic relation extraction and automatic translation to SPARQL queries. Our study supports the fact that SPARQL can represent a wide range of natural language questions in a question-answering perspective. Experiments on a corpus of real questions show that we obtain encouraging results in medical entity recognition and relation extraction. The obtained results also show that the output SPARQL queries correctly represent more than 60% of the original questions.