Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network

  title={Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network},
  author={Sunil Kumar Sahu and Ashish Anand},
  journal={Journal of biomedical informatics},

Applying Self-interaction Attention for Extracting Drug-Drug Interactions

A model that combines bidirectional Long Short Term Memory (LSTM) networks with the Self-Interaction Attention Mechanism is proposed that improves the classification accuracy reducing the tendency to predict the majority class resulting in false negatives, over several input configurations.

Position-aware deep multi-task learning for drug-drug interaction extraction

Drug-Drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers

Inspired by the deep learning approaches in natural language processing, a recurrent neural network model with multiple attention layers for DDI classification is proposed that outperforms the existing NLP or deep learning methods.

Drug-Drug Interaction Extraction via Recurrent Hybrid Convolutional Neural Networks with an Improved Focal Loss

A novel recurrent hybrid convolutional neural network (RHCNN) for DDI extraction from biomedical literature and applies an improved focal loss function to mitigate against the defects of the traditional cross-entropy loss function when dealing with class imbalanced data.

Deep Convolution Neural Networks for Drug-Drug Interaction Extraction

A deep convolutional neural network (DCNN) based on DDI extraction method is presented, which obtains a better result than other state-of-the-art methods and increases as the network gets deeper and hits its peak at depth 16.

Leveraging Biomedical Resources in Bi-LSTM for Drug-Drug Interaction Extraction

A new bidirectional long–short-term memory (L STM) network-based method, namely, biomedical resource LSTM (BR-LSTM), which combines biomedical resource with lexical information and entity position information together to extract DDI from the biomedical literature is proposed.

Extracting Drug-drug Interactions with a Dependency-based Graph Convolution Neural Network

This article proposed a model that combines the graph convolution neural network (GCNN) and bidirectional long short-term memory (BiLSTM) to extract DDI interactions from entire dependency graphs of sentences to improve DDI extraction.



Extracting Drug-Drug Interactions with Word and Character-Level Recurrent Neural Networks

This paper is the first to investigate the potential of character-level RNNs (Char-RNNs) for DDI extraction (and relation extraction in general), and finds that ensembling models from both architectures results in nontrivial gains over simply using either alone, indicating that they complement each other.

Drug drug interaction extraction from the literature using a recursive neural network

A recursive neural network model uses a position feature, a subtree containment feature, and an ensemble method to improve the performance of DDI extraction and demonstrates that this model can automatically extract DDIs better than existing models.

Drug–drug interaction extraction via hierarchical RNNs on sequence and shortest dependency paths

A hierarchical recurrent neural networks (RNNs)‐based method to integrate the SDP and sentence sequence for DDI extraction task and experimental results show that the sentence sequence and SDP are complementary to each other.

Drug-Drug Interaction Extraction via Convolutional Neural Networks

This work proposed a CNN-based method for DDI extraction that achieves an F-score of 69.75%, which outperforms the existing best performing method by 2.75% and demonstrates that CNN is a good choice for D DI extraction.

UWM-TRIADS: Classifying Drug-Drug Interactions with Two-Stage SVM and Post-Processing

This work describes the use of a two-stage weighted SVM classifier to handle the highly unbalanced class distribution of Drug-Drug interactions given labeled drug mentions, and developed a set of post-processing rules based on observations in the training data.

Extracting Drug-Drug Interactions with Attention CNNs

This work proposes a novel attention mechanism for a Convolutional Neural Network (CNN)-based Drug-Drug Interaction (DDI) extraction model that improves the performance of the base CNN-based DDI model and is competitive with the state-of-the-art models.

FBK-irst : A Multi-Phase Kernel Based Approach for Drug-Drug Interaction Detection and Classification that Exploits Linguistic Information

The proposed approach indirectly (and automatically) exploits the scope of negation cues and the semantic roles of involved entities for reducing the skewness in the training data as well as discarding possible negative instances from the test data.

UTurku: Drug Named Entity Recognition and Drug-Drug Interaction Extraction Using SVM Classification and Domain Knowledge

This work applies the machine learning based Turku Event Extraction System to the detection of drug names and statements of drug-drug interactions (DDI) from text and achieves F-scores of 60% and 59% for the drug name recognition task and DDI extraction task respectively.