Tilia Ellendorff, Lenz Furrer, N. Colic, Noëmi Aepli, Fabio Rinaldi
We describe our submissions to the 4th edition of the Social Media Mining for Health Applications (SMM4H) shared task. Our team (UZH) participated in two sub-tasks: Automatic classifications of adverse effects mentions in tweets (Task 1) and Generalizable identification of personal health experience mentions (Task 4). For our submissions, we exploited ensembles based on a pre-trained language representation with a neural transformer architecture (BERT) (Tasks 1 and 4) and a CNN-BiLSTM(-CRF) network within a multi-task learning scenario (Task 1). These systems are placed on top of a carefully crafted pipeline of domain-specific preprocessing steps.
{"title":"Approaching SMM4H with Merged Models and Multi-task Learning","authors":"Tilia Ellendorff, Lenz Furrer, N. Colic, Noëmi Aepli, Fabio Rinaldi","doi":"10.18653/v1/W19-3208","DOIUrl":"https://doi.org/10.18653/v1/W19-3208","url":null,"abstract":"We describe our submissions to the 4th edition of the Social Media Mining for Health Applications (SMM4H) shared task. Our team (UZH) participated in two sub-tasks: Automatic classifications of adverse effects mentions in tweets (Task 1) and Generalizable identification of personal health experience mentions (Task 4). For our submissions, we exploited ensembles based on a pre-trained language representation with a neural transformer architecture (BERT) (Tasks 1 and 4) and a CNN-BiLSTM(-CRF) network within a multi-task learning scenario (Task 1). These systems are placed on top of a carefully crafted pipeline of domain-specific preprocessing steps.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126305317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper describes the system developed by team ASU-NLP for the Social Media Mining for Health Applications(SMM4H) shared task 4. We extract feature embeddings from the BioBERT (Lee et al., 2019) model which has been fine-tuned on the training dataset and use that as inputs to a dense fully connected neural network. We achieve above average scores among the participant systems with the overall F1-score, accuracy, precision, recall as 0.8036, 0.8456, 0.9783, 0.6818 respectively.
本文描述了由ASU-NLP团队为健康应用的社交媒体挖掘(SMM4H)共享任务4开发的系统。我们从BioBERT (Lee et al.， 2019)模型中提取特征嵌入，该模型已经在训练数据集上进行了微调，并将其用作密集全连接神经网络的输入。我们在参与者系统中取得了高于平均水平的成绩，总体f1得分、准确率、精密度、召回率分别为0.8036、0.8456、0.9783、0.6818。
{"title":"Neural Network to Identify Personal Health Experience Mention in Tweets Using BioBERT Embeddings","authors":"Shubham Gondane","doi":"10.18653/v1/W19-3218","DOIUrl":"https://doi.org/10.18653/v1/W19-3218","url":null,"abstract":"This paper describes the system developed by team ASU-NLP for the Social Media Mining for Health Applications(SMM4H) shared task 4. We extract feature embeddings from the BioBERT (Lee et al., 2019) model which has been fine-tuned on the training dataset and use that as inputs to a dense fully connected neural network. We achieve above average scores among the participant systems with the overall F1-score, accuracy, precision, recall as 0.8036, 0.8456, 0.9783, 0.6818 respectively.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128690222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social Media Mining for Health Applications (SMM4H) Adverse Effect Mentions Shared Task challenges participants to accurately identify spans of text within a tweet that correspond to Adverse Effects (AEs) resulting from medication usage (Weissenbacher et al., 2019). This task features a training data set of 2,367 tweets, in addition to a 1,000 tweet evaluation data set. The solution presented here features a bidirectional Long Short-term Memory Network (bi-LSTM) for the generation of character-level embeddings. It uses a second bi-LSTM trained on both character and token level embeddings to feed a Conditional Random Field (CRF) which provides the final classification. This paper further discusses the deep learning algorithms used in our solution.
{"title":"Deep Learning for Identification of Adverse Effect Mentions In Twitter Data","authors":"P. Barry, Ozlem Uzuner","doi":"10.18653/v1/W19-3215","DOIUrl":"https://doi.org/10.18653/v1/W19-3215","url":null,"abstract":"Social Media Mining for Health Applications (SMM4H) Adverse Effect Mentions Shared Task challenges participants to accurately identify spans of text within a tweet that correspond to Adverse Effects (AEs) resulting from medication usage (Weissenbacher et al., 2019). This task features a training data set of 2,367 tweets, in addition to a 1,000 tweet evaluation data set. The solution presented here features a bidirectional Long Short-term Memory Network (bi-LSTM) for the generation of character-level embeddings. It uses a second bi-LSTM trained on both character and token level embeddings to feed a Conditional Random Field (CRF) which provides the final classification. This paper further discusses the deep learning algorithms used in our solution.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127440229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, we describe our methods to automatically classify Twitter posts conveying events of adverse drug reaction (ADR). Based on our previous experience in tackling the ADR classification task, we empirically applied the vote-based under-sampling ensemble approach along with linear support vector machine (SVM) to develop our classifiers as part of our participation in ACL 2019 Social Media Mining for Health Applications (SMM4H) shared task 1. The best-performed model on the test sets were trained on a merged corpus consisting of the datasets released by SMM4H 2017 and 2019. By using VUE, the corpus was randomly under-sampled with 2:1 ratio between the negative and positive classes to create an ensemble using the linear kernel trained with features including bag-of-word, domain knowledge, negation and word embedding. The best performing model achieved an F-measure of 0.551 which is about 5% higher than the average F-scores of 16 teams.
{"title":"BIGODM System in the Social Media Mining for Health Applications Shared Task 2019","authors":"Chen-Kai Wang, Hong-Jie Dai, Bo-Hung Wang","doi":"10.18653/v1/W19-3220","DOIUrl":"https://doi.org/10.18653/v1/W19-3220","url":null,"abstract":"In this study, we describe our methods to automatically classify Twitter posts conveying events of adverse drug reaction (ADR). Based on our previous experience in tackling the ADR classification task, we empirically applied the vote-based under-sampling ensemble approach along with linear support vector machine (SVM) to develop our classifiers as part of our participation in ACL 2019 Social Media Mining for Health Applications (SMM4H) shared task 1. The best-performed model on the test sets were trained on a merged corpus consisting of the datasets released by SMM4H 2017 and 2019. By using VUE, the corpus was randomly under-sampled with 2:1 ratio between the negative and positive classes to create an ensemble using the linear kernel trained with features including bag-of-word, domain knowledge, negation and word embedding. The best performing model achieved an F-measure of 0.551 which is about 5% higher than the average F-scores of 16 teams.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114579854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Dirkson, S. Verberne, G. van Oortmerssen, Wessel Kraaij
In the medical domain, user-generated social media text is increasingly used as a valuable complementary knowledge source to scientific medical literature. The extraction of this knowledge is complicated by colloquial language use and misspellings. Yet, lexical normalization of such data has not been addressed properly. This paper presents an unsupervised, data-driven spelling correction module for medical social media. Our method outperforms state-of-the-art spelling correction and can detect mistakes with an F0.5 of 0.888. Additionally, we present a novel corpus for spelling mistake detection and correction on a medical patient forum.
{"title":"Lexical Normalization of User-Generated Medical Text","authors":"A. Dirkson, S. Verberne, G. van Oortmerssen, Wessel Kraaij","doi":"10.18653/v1/W19-3202","DOIUrl":"https://doi.org/10.18653/v1/W19-3202","url":null,"abstract":"In the medical domain, user-generated social media text is increasingly used as a valuable complementary knowledge source to scientific medical literature. The extraction of this knowledge is complicated by colloquial language use and misspellings. Yet, lexical normalization of such data has not been addressed properly. This paper presents an unsupervised, data-driven spelling correction module for medical social media. Our method outperforms state-of-the-art spelling correction and can detect mistakes with an F0.5 of 0.888. Additionally, we present a novel corpus for spelling mistake detection and correction on a medical patient forum.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123175983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper details our approach to the task of detecting reportage of adverse drug reaction in tweets as part of the 2019 social media mining for healthcare applications shared task. We employed a combination of three types of word representations as input to a LSTM model. With this approach, we achieved an F1 score of 0.5209.
{"title":"Detection of Adverse Drug Reaction in Tweets Using a Combination of Heterogeneous Word Embeddings","authors":"S. Aroyehun, Alexander Gelbukh","doi":"10.18653/v1/W19-3224","DOIUrl":"https://doi.org/10.18653/v1/W19-3224","url":null,"abstract":"This paper details our approach to the task of detecting reportage of adverse drug reaction in tweets as part of the 2019 social media mining for healthcare applications shared task. We employed a combination of three types of word representations as input to a LSTM model. With this approach, we achieved an F1 score of 0.5209.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131899077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Javier Cortes-Tejada, Juan Martínez-Romo, Lourdes Araujo
This paper describes a system for automatically classifying adverse effects mentions in tweets developed for the task 1 at Social Media Mining for Health Applications (SMM4H) Shared Task 2019. We have developed a system based on LSTM neural networks inspired by the excellent results obtained by deep learning classifiers in the last edition of this task. The network is trained along with Twitter GloVe pre-trained word embeddings.
{"title":"NLP@UNED at SMM4H 2019: Neural Networks Applied to Automatic Classifications of Adverse Effects Mentions in Tweets","authors":"Javier Cortes-Tejada, Juan Martínez-Romo, Lourdes Araujo","doi":"10.18653/v1/W19-3213","DOIUrl":"https://doi.org/10.18653/v1/W19-3213","url":null,"abstract":"This paper describes a system for automatically classifying adverse effects mentions in tweets developed for the task 1 at Social Media Mining for Health Applications (SMM4H) Shared Task 2019. We have developed a system based on LSTM neural networks inspired by the excellent results obtained by deep learning classifiers in the last edition of this task. The network is trained along with Twitter GloVe pre-trained word embeddings.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128095978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
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 subtasks are automatic classification and extraction of adverse effect mentions in tweets. The systems for the two subtasks are based on bidirectional encoder representations from transformers (BERT), and achieves promising results. Among the systems we developed for subtask1, the best F1-score was 0.6457, for subtask2, the best relaxed F1-score and the best strict F1-score were 0.614 and 0.407 respectively. Our system ranks first among all systems on subtask1.
{"title":"HITSZ-ICRC: A Report for SMM4H Shared Task 2019-Automatic Classification and Extraction of Adverse Effect Mentions in Tweets","authors":"Shuai Chen, Yuanhang Huang, Xiao-Ping Huang, Haoming Qin, Jun Yan, Buzhou Tang","doi":"10.18653/v1/W19-3206","DOIUrl":"https://doi.org/10.18653/v1/W19-3206","url":null,"abstract":"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 subtasks are automatic classification and extraction of adverse effect mentions in tweets. The systems for the two subtasks are based on bidirectional encoder representations from transformers (BERT), and achieves promising results. Among the systems we developed for subtask1, the best F1-score was 0.6457, for subtask2, the best relaxed F1-score and the best strict F1-score were 0.614 and 0.407 respectively. Our system ranks first among all systems on subtask1.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122603612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V.G.Vinod Vydiswaran, Grace Ganzel, Bryan Romas, D. Yu, Amy M. Austin, N. Bhomia, S. Chan, S. Hall, Van Le, Aaron Miller, Olawunmi Oduyebo, Aulia Song, Radhika Sondhi, D. Teng, H. Tseng, Kim Vuong, Stephanie Zimmerman
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 tweets, and training traditional machine learning and deep learning models. Our submitted runs performed above average for the task.
{"title":"Towards Text Processing Pipelines to Identify Adverse Drug Events-related Tweets: University of Michigan @ SMM4H 2019 Task 1","authors":"V.G.Vinod Vydiswaran, Grace Ganzel, Bryan Romas, D. Yu, Amy M. Austin, N. Bhomia, S. Chan, S. Hall, Van Le, Aaron Miller, Olawunmi Oduyebo, Aulia Song, Radhika Sondhi, D. Teng, H. Tseng, Kim Vuong, Stephanie Zimmerman","doi":"10.18653/v1/W19-3217","DOIUrl":"https://doi.org/10.18653/v1/W19-3217","url":null,"abstract":"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 tweets, and training traditional machine learning and deep learning models. Our submitted runs performed above average for the task.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126902937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper describes a system developed for the Social Media Mining for Health (SMM4H) 2019 shared tasks. Specifically, we participated in three tasks. The goals of the first two tasks are to classify whether a tweet contains mentions of adverse drug reactions (ADR) and extract these mentions, respectively. The objective of the third task is to build an end-to-end solution: first, detect ADR mentions and then map these entities to concepts in a controlled vocabulary. We investigate the use of a language representation model BERT trained to obtain semantic representations of social media texts. Our experiments on a dataset of user reviews showed that BERT is superior to state-of-the-art models based on recurrent neural networks. The BERT-based system for Task 1 obtained an F1 of 57.38%, with improvements up to +7.19% F1 over a score averaged across all 43 submissions. The ensemble of neural networks with a voting scheme for named entity recognition ranked first among 9 teams at the SMM4H 2019 Task 2 and obtained a relaxed F1 of 65.8%. The end-to-end model based on BERT for ADR normalization ranked first at the SMM4H 2019 Task 3 and obtained a relaxed F1 of 43.2%.
{"title":"KFU NLP Team at SMM4H 2019 Tasks: Want to Extract Adverse Drugs Reactions from Tweets? BERT to The Rescue","authors":"Z. Miftahutdinov, I. Alimova, E. Tutubalina","doi":"10.18653/v1/W19-3207","DOIUrl":"https://doi.org/10.18653/v1/W19-3207","url":null,"abstract":"This paper describes a system developed for the Social Media Mining for Health (SMM4H) 2019 shared tasks. Specifically, we participated in three tasks. The goals of the first two tasks are to classify whether a tweet contains mentions of adverse drug reactions (ADR) and extract these mentions, respectively. The objective of the third task is to build an end-to-end solution: first, detect ADR mentions and then map these entities to concepts in a controlled vocabulary. We investigate the use of a language representation model BERT trained to obtain semantic representations of social media texts. Our experiments on a dataset of user reviews showed that BERT is superior to state-of-the-art models based on recurrent neural networks. The BERT-based system for Task 1 obtained an F1 of 57.38%, with improvements up to +7.19% F1 over a score averaged across all 43 submissions. The ensemble of neural networks with a voting scheme for named entity recognition ranked first among 9 teams at the SMM4H 2019 Task 2 and obtained a relaxed F1 of 65.8%. The end-to-end model based on BERT for ADR normalization ranked first at the SMM4H 2019 Task 3 and obtained a relaxed F1 of 43.2%.","PeriodicalId":265570,"journal":{"name":"Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116983806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：