Clinical information extraction applications: A literature review.

Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc. NER systems have been studied and developed widely for decades, but accurate systems using deep neural networks (NN) have only been introduced in the last few years. We present a comprehensive survey of deep neural network architectures for NER, and contrast them with previous approaches to NER based on feature engineering and other supervised or semi-supervised learning algorithms. Our results highlight the improvements achieved by neural networks, and show how incorporating some of the lessons learned from past work on feature-based NER systems can yield further improvements.

A Survey on Recent Advances in Named Entity Recognition from Deep Learning models

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence ...

/pdf/constructing-datasets-for-multi-hop-reading-comprehension-5e7b7cv3zf.pdf

Constructing Datasets for Multi-hop Reading Comprehension Across Documents

The DDI corpus

A comparison of word embeddings for the biomedical natural language processing

The DDIExtraction 2013 task concerns the recognition of drugs and extraction of drugdrug interactions that appear in biomedical literature. We propose two subtasks for the DDIExtraction 2013 Shared Task challenge: 1) the recognition and classification of drug names and 2) the extraction and classification of their interactions. Both subtasks have been very successful in participation and results. There were 14 teams who submitted a total of 38 runs. The best result reported for the first subtask was F1 of 71.5% and 65.1% for the second one.

SemEval-2013 Task 9 : Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013)

Artificial neural networks (ANNs) have been developed to predict the clinical significance of drug-drug interactions (DDIs) for a set of 35 pharmaceutical drugs using data compiled from the Web-based resources, Lexicomp® and Vidal®, with inputs furnished by various drug pharmacokinetic (PK) and/or pharmacodynamic (PD) properties, and/or drug-enzyme interaction data. Success in prediction of DDI significance was found to vary according to the drug properties used as ANN input, and also varied with the DDI dataset used in training. The Lexicomp® dataset is found to give predictions marginally better than those obtained using the Vidal® dataset, with the best prediction of minor DDIs achieved using a multi-layer perceptron (MLP) model trained using enzyme variables alone (F1 82%) and the best prediction of major DDIs achieved using a MLP model trained on PK/PD properties alone (F1 54%). Given a more comprehensive and more consistent dataset of DDI data, we conclude that machine learning tools could be used to acquire new knowledge on DDIs, and could thus facilitate the regulatory agencies’ pharmocovigilance of newly licensed drugs.

Mar'ia Herrero Zazo

Papers

SemEval-2013 Task 9 : Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013)

Application of Machine Learning in Knowledge Discovery for Pharmaceutical Drug-drug Interactions