Extracting Drug-Drug Interactions with Attention CNNs

Asada, Masaki; Misawa, Miwa; Sasaki, Yutaka

doi:10.18653/v1/w17-2302

Cited by 27 publications

(21 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For drug-drug interactions, Zhao et al [92] used a CNN that employs word embeddings with the syntactic information of a sentence as well as features of part-of-speech tags and dependency trees. Asada et al [93] experimented with an attention CNN, and Yi et al [94] proposed an RNN model with multiple attention layers. In both cases, it is a single model with attention mechanism, which allows the decoder to focus on different parts of the source sentence.…”

Section: Text Applications In Healthcarementioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2018

J. R. Soc. Interface.

1,570

1,001

View full text Add to dashboard Cite

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems—patient classification, fundamental biological processes and treatment of patients—and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

show abstract

Section: Text Applications In Healthcarementioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2018

J. R. Soc. Interface.

1,570

1,001

View full text Add to dashboard Cite

show abstract

“…A common feature of the works in this domain, noted by (Zhou et al, 2014;Lever and Jones, 2017) and still relevant for recent works e.g. (Peng and Lu, 2017;Asada et al, 2017), consists in assuming that entities of interest are already extracted and provided to the relation extraction system as input. Thus, the relation extraction is assessed separately, without taking into account the performance of entity extraction.…”

Section: Relation Extractionmentioning

confidence: 99%

Extracting relations between outcomes and significance levels in Randomized Controlled Trials (RCTs) publications

Koroleva¹,

Paroubek²

2019

Proceedings of the 18th BioNLP Workshop and Shared Task

View full text Add to dashboard Cite

Randomized controlled trials assess the effects of an experimental intervention by comparing it to a control intervention with regard to some variables-trial outcomes. Statistical hypothesis testing is used to test if the experimental intervention is superior to the control. Statistical significance is typically reported for the measured outcomes and is an important characteristic of the results. We propose a machine learning approach to automatically extract reported outcomes, significance levels and the relation between them. We annotated a corpus of 663 sentences with 2,552 outcomesignificance level relations (1,372 positive and 1,180 negative relations). We compared several classifiers, using a manually crafted feature set, and a number of deep learning models. The best performance (F-measure of 94%) was shown by the BioBERT fine-tuned model.

show abstract

“…After adversarial training we would expect the test instances to align with training instances such that it looks like the test dataset was sampled evenly across the training data distribution 2017). Meanwhile, both CNN (Asada et al, 2017;Liu et al, 2016;Matos and Antunes, 2017) and long short-term memory networks (LSTM) have worked well for DDI classification (Kavuluru et al, 2017;Zhang et al, 2017).…”

Section: Relation Classificationmentioning

confidence: 99%