Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets
This paper presents our contribution to the Social Media Mining for Health Applications Shared Task 2021. We addressed all the three subtasks of Task 1: Subtask A (classification of tweets containing adverse effects), Subtask B (extraction of text spans containing adverse effects) and Subtask C (adverse effects resolution). We explored various pre-trained transformer-based language models and we focused on a multi-task training architecture. For the first subtask, we also applied adversarial augmentation techniques and we formed model ensembles in order to improve the robustness of the prediction. Our system ranked first at Subtask B with 0.51 F1 score, 0.514 precision and 0.514 recall. For Subtask A we obtained 0.44 F1 score, 0.49 precision and 0.39 recall and for Subtask C we obtained 0.16 F1 score with 0.16 precision and 0.17 recall.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Task LearningSimilar Papers 제목 키워드 기반
BioInfo@UAVR@SMM4H’22: Classification and Extraction of Adverse Event mentions in Tweets using Transformer Models
This paper describes BioInfo@UAVR team’s approach for adressing subtasks 1a and 1b of the Social Media Mining for Health Applications 2022 shared task. These sub-tasks deal with the classification of tweets that contain …
Data AugmentationSentence Transformers and Bayesian Optimization for Adverse Drug Effect Detection from Twitter
This paper describes our approach for detecting adverse drug effect mentions on Twitter as part of the Social Media Mining for Health Applications (SMM4H) 2020, Shared Task 2. Our approach utilizes multilingual sentence …
Bayesian OptimizationHyperparameter OptimizationSentenceSentence Embeddings+1UB Health Miners@SMM4H’22: Exploring Pre-processing Techniques To Classify Tweets Using Transformer Based Pipelines.
Here we discuss our implementation of two tasks in the Social Media Mining for Health Applications (SMM4H) 2022 shared tasks – classification, detection, and normalization of Adverse Events (AE) mentioned in English twee…
Binary ClassificationClassificationMulti-class Classificationnamed-entity-recognition+3Autobots Ensemble: Identifying and Extracting Adverse Drug Reaction from Tweets Using Transformer Based Pipelines
This paper details a system designed for Social Media Mining for Health Applications (SMM4H) Shared Task 2020. We specifically describe the systems designed to solve task 2: Automatic classification of multilingual tweet…
NERQuestion AnsweringTask 2HITSZ-ICRC: A Report for SMM4H Shared Task 2019-Automatic Classification and Extraction of Adverse Effect Mentions in Tweets
This is the system description of the Harbin Institute of Technology Shenzhen (HITSZ) team for the first and second subtasks of the fourth Social Media Mining for Health Applications (SMM4H) shared task in 2019. The two …