Identifying Adverse Drug Events Mentions in Tweets Using Attentive, Collocated, and Aggregated Medical Representation

2019-08-01 · WS 2019 8 · Xinyan Zhao, Deahan Yu, V.G.Vinod Vydiswaran

Identifying mentions of medical concepts in social media is challenging because of high variability in free text. In this paper, we propose a novel neural network architecture, the Collocated LSTM with Attentive Pooling and Aggregated representation (CLAPA), that integrates a bidirectional LSTM model with attention and pooling strategy and utilizes the collocation information from training data to improve the representation of medical concepts. The collocation and aggregation layers improve the model performance on the task of identifying mentions of adverse drug events (ADE) in tweets. Using the dataset made available as part of the workshop shared task, we show that careful selection of neighborhood contexts can help uncover useful local information and improve the overall medical concept representation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Towards Text Processing Pipelines to Identify Adverse Drug Events-related Tweets: University of Michigan @ SMM4H 2019 Task 1

2019-08-01 · WS 2019 8 · V.G.Vinod Vydiswaran, Grace Ganzel, Bryan Romas, Deahan Yu 외

We participated in Task 1 of the Social Media Mining for Health Applications (SMM4H) 2019 Shared Tasks on detecting mentions of adverse drug events (ADEs) in tweets. Our approach relied on a text processing pipeline for …

BIG-bench Machine Learning

MIDAS@SMM4H-2019: Identifying Adverse Drug Reactions and Personal Health Experience Mentions from Twitter

2019-08-01 · ACL 2019 8

In this paper, we present our approach and the system description for the Social Media Mining for Health Applications (SMM4H) Shared Task 1,2 and 4 (2019). Our main contribution is to show the effectiveness of Transfer L…

Transfer Learning

Identifying Potential Adverse Drug Events in Tweets Using Bootstrapped Lexicons

2016-08-01 · ACL 2016 8 · Eric Benzschawel

Multi-Task Learning for Extraction of Adverse Drug Reaction Mentions from Tweets

2018-02-14 · Shashank Gupta, Manish Gupta, Vasudeva Varma, Sachin Pawar 외

Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care. Current ADR surveillance systems are often associated with a substantial time lag before such events are officially published. On t…

Event Detection Multi-Task Learning

Co-training for Extraction of Adverse Drug Reaction Mentions from Tweets