TY - JOUR
T1 - Automatic grading of evidence
T2 - Australasian Language Technology Workshop (9th : 2011)
AU - Mollá, Diego
AU - Sarker, Abeed
N1 - Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
PY - 2011
Y1 - 2011
N2 - The ALTA shared tasks are programming competitions where all participants attempt to
solve the same problem, and the winner is the system with the best results. The 2011 ALTA shared task is the second in the series and it focuses on trying to automatically grade the level of clinical evidence in medical research papers. In this paper we describe the task, present the results of several baselines, and the
results of our method. We apply a sequence of high precision machine learning classifiers with varying feature sets for each. In addition to using n-grams, we incorporate domain knowledge by representing specific medical concepts using their semantic categories. We also apply a specialised rule-based approach for automatically identifying the publication types of articles, which is then used as a feature set. Our approach obtains an accuracy of 62.84% which is a significant improvement over the baselines.
AB - The ALTA shared tasks are programming competitions where all participants attempt to
solve the same problem, and the winner is the system with the best results. The 2011 ALTA shared task is the second in the series and it focuses on trying to automatically grade the level of clinical evidence in medical research papers. In this paper we describe the task, present the results of several baselines, and the
results of our method. We apply a sequence of high precision machine learning classifiers with varying feature sets for each. In addition to using n-grams, we incorporate domain knowledge by representing specific medical concepts using their semantic categories. We also apply a specialised rule-based approach for automatically identifying the publication types of articles, which is then used as a feature set. Our approach obtains an accuracy of 62.84% which is a significant improvement over the baselines.
UR - http://www.scopus.com/inward/record.url?scp=84930577162&partnerID=8YFLogxK
M3 - Conference paper
SP - 4
EP - 8
JO - Proceedings of the Australasian Language Technology Association Workshop 2011
JF - Proceedings of the Australasian Language Technology Association Workshop 2011
SN - 1834-7037
Y2 - 1 December 2011 through 2 December 2011
ER -