TY - GEN
T1 - Dependency and AMR embeddings for drug-drug interaction extraction from biomedical literature
AU - Wang, Yanshan
AU - Wang, Liwei
AU - Liu, Sijia
AU - Shen, Feichen
AU - Liu, Hongfang
AU - Rastegar-Mojarad, Majid
AU - Liu, Fei
N1 - Publisher Copyright:
© 2017 ACM.
PY - 2017/8/20
Y1 - 2017/8/20
N2 - Drug-drug interaction (DDI) is an unexpected change in a drug's effect on the human body when the drug and a second drug are co-prescribed and taken together. As many DDIs are frequently reported in biomedical literature, it is important to mine DDI information from literature to keep DDI knowledge up to date. One of the SemEval challenges in the year 2011 and 2013 was designed to tackle the task where the best system achieved an F1 score of 0.80. In this paper, we propose to utilize dependency embeddings and Abstract Meaning Representation (AMR) embeddings as features for extracting DDIs. Our contribution is two-fold. First, we employed dependency embeddings, previously shown effective for sentence classification, for DDI extraction. The dependency embeddings incorporated structural syntactic contexts into the embeddings, which were not present in the conventional word embeddings. Second, we proposed a novel syntactic embedding approach using AMR. AMR aims to abstract away from syntactic idiosyncrasies and attempts to capture only the core meaning of a sentence, which could potentially improve DDI extraction from sentences. Two classifiers (Support Vector Machine and Random Forest) taking these embedding features as input were evaluated on the DDIExtraction 2013 challenge corpus. The experimental results show the effectiveness of dependency and AMR embeddings in the DDI extraction task. The best performance was obtained by combining word, dependency and AMR embeddings (F1 score=0.84).
AB - Drug-drug interaction (DDI) is an unexpected change in a drug's effect on the human body when the drug and a second drug are co-prescribed and taken together. As many DDIs are frequently reported in biomedical literature, it is important to mine DDI information from literature to keep DDI knowledge up to date. One of the SemEval challenges in the year 2011 and 2013 was designed to tackle the task where the best system achieved an F1 score of 0.80. In this paper, we propose to utilize dependency embeddings and Abstract Meaning Representation (AMR) embeddings as features for extracting DDIs. Our contribution is two-fold. First, we employed dependency embeddings, previously shown effective for sentence classification, for DDI extraction. The dependency embeddings incorporated structural syntactic contexts into the embeddings, which were not present in the conventional word embeddings. Second, we proposed a novel syntactic embedding approach using AMR. AMR aims to abstract away from syntactic idiosyncrasies and attempts to capture only the core meaning of a sentence, which could potentially improve DDI extraction from sentences. Two classifiers (Support Vector Machine and Random Forest) taking these embedding features as input were evaluated on the DDIExtraction 2013 challenge corpus. The experimental results show the effectiveness of dependency and AMR embeddings in the DDI extraction task. The best performance was obtained by combining word, dependency and AMR embeddings (F1 score=0.84).
KW - Abstract Meaning Representation
KW - Deep learning
KW - Dependency
KW - Drug-drug interaction
KW - Embeddings
UR - http://www.scopus.com/inward/record.url?scp=85031316038&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85031316038&partnerID=8YFLogxK
U2 - 10.1145/3107411.3107426
DO - 10.1145/3107411.3107426
M3 - Conference contribution
AN - SCOPUS:85031316038
T3 - ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
SP - 36
EP - 43
BT - ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
PB - Association for Computing Machinery, Inc
T2 - 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017
Y2 - 20 August 2017 through 23 August 2017
ER -