Pub Date : 1900-01-01DOI: 10.18653/v1/2021.bionlp-1.3
Pieter Fivez, Simon Suster, Walter Daelemans
Recent research on robust representations of biomedical names has focused on modeling large amounts of fine-grained conceptual distinctions using complex neural encoders. In this paper, we explore the opposite paradigm: training a simple encoder architecture using only small sets of names sampled from high-level biomedical concepts. Our encoder post-processes pretrained representations of biomedical names, and is effective for various types of input representations, both domain-specific or unsupervised. We validate our proposed few-shot learning approach on multiple biomedical relatedness benchmarks, and show that it allows for continual learning, where we accumulate information from various conceptual hierarchies to consistently improve encoder performance. Given these findings, we propose our approach as a low-cost alternative for exploring the impact of conceptual distinctions on robust biomedical name representations.
{"title":"Scalable Few-Shot Learning of Robust Biomedical Name Representations","authors":"Pieter Fivez, Simon Suster, Walter Daelemans","doi":"10.18653/v1/2021.bionlp-1.3","DOIUrl":"https://doi.org/10.18653/v1/2021.bionlp-1.3","url":null,"abstract":"Recent research on robust representations of biomedical names has focused on modeling large amounts of fine-grained conceptual distinctions using complex neural encoders. In this paper, we explore the opposite paradigm: training a simple encoder architecture using only small sets of names sampled from high-level biomedical concepts. Our encoder post-processes pretrained representations of biomedical names, and is effective for various types of input representations, both domain-specific or unsupervised. We validate our proposed few-shot learning approach on multiple biomedical relatedness benchmarks, and show that it allows for continual learning, where we accumulate information from various conceptual hierarchies to consistently improve encoder performance. Given these findings, we propose our approach as a low-cost alternative for exploring the impact of conceptual distinctions on robust biomedical name representations.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114426355","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}
M. Nagata, Kohichi Takai, K. Yasuda, P. Heracleous, Akio Yoneyama
This study focuses on highly accurate prediction of the onset of type-2 diabetes. We investigated whether prediction accuracy can be improved by utilizing lab test data obtained from health checkups and incorporating health claim text data such as medically diagnosed diseases with ICD10 codes and pharmacy information. In a previous study, prediction accuracy was increased slightly by adding diagnosis disease name and independent variables such as prescription medicine. Therefore, in the current study we explored more suitable models for prediction by using state-of-the-art techniques such as XGBoost and long short-term memory (LSTM) based on recurrent neural networks. In the current study, text data was vectorized using word2vec, and the prediction model was compared with logistic regression. The results obtained confirmed that onset of type-2 diabetes can be predicted with a high degree of accuracy when the XGBoost model is used.
{"title":"Prediction Models for Risk of Type-2 Diabetes Using Health Claims","authors":"M. Nagata, Kohichi Takai, K. Yasuda, P. Heracleous, Akio Yoneyama","doi":"10.18653/v1/W18-2322","DOIUrl":"https://doi.org/10.18653/v1/W18-2322","url":null,"abstract":"This study focuses on highly accurate prediction of the onset of type-2 diabetes. We investigated whether prediction accuracy can be improved by utilizing lab test data obtained from health checkups and incorporating health claim text data such as medically diagnosed diseases with ICD10 codes and pharmacy information. In a previous study, prediction accuracy was increased slightly by adding diagnosis disease name and independent variables such as prescription medicine. Therefore, in the current study we explored more suitable models for prediction by using state-of-the-art techniques such as XGBoost and long short-term memory (LSTM) based on recurrent neural networks. In the current study, text data was vectorized using word2vec, and the prediction model was compared with logistic regression. The results obtained confirmed that onset of type-2 diabetes can be predicted with a high degree of accuracy when the XGBoost model is used.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128299150","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}
We present a machine learning pipeline that identifies key sentences in abstracts of oncological articles to aid evidence-based medicine. This problem is characterized by the lack of gold standard datasets, data imbalance and thematic differences between available silver standard corpora. Additionally, available training and target data differs with regard to their domain (professional summaries vs. sentences in abstracts). This makes supervised machine learning inapplicable. We propose the use of two semi-supervised machine learning approaches: To mitigate difficulties arising from heterogeneous data sources, overcome data imbalance and create reliable training data we propose using transductive learning from positive and unlabelled data (PU Learning). For obtaining a realistic classification model, we propose the use of abstracts summarised in relevant sentences as unlabelled examples through Self-Training. The best model achieves 84% accuracy and 0.84 F1 score on our dataset
{"title":"Identifying Key Sentences for Precision Oncology Using Semi-Supervised Learning","authors":"J. Seva, Martin Wackerbauer, U. Leser","doi":"10.18653/v1/W18-2305","DOIUrl":"https://doi.org/10.18653/v1/W18-2305","url":null,"abstract":"We present a machine learning pipeline that identifies key sentences in abstracts of oncological articles to aid evidence-based medicine. This problem is characterized by the lack of gold standard datasets, data imbalance and thematic differences between available silver standard corpora. Additionally, available training and target data differs with regard to their domain (professional summaries vs. sentences in abstracts). This makes supervised machine learning inapplicable. We propose the use of two semi-supervised machine learning approaches: To mitigate difficulties arising from heterogeneous data sources, overcome data imbalance and create reliable training data we propose using transductive learning from positive and unlabelled data (PU Learning). For obtaining a realistic classification model, we propose the use of abstracts summarised in relevant sentences as unlabelled examples through Self-Training. The best model achieves 84% accuracy and 0.84 F1 score on our dataset","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128697593","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.bionlp-1.29
Liwen Xu, Yan Zhang, Lei Hong, Yi Cai, Szui Sung
In this article, we will describe our system for MEDIQA2021 shared tasks. First, we will describe the method of the second task, multiple answer summary (MAS). For extracting abstracts, we follow the rules of (CITATION). First, the candidate sentences are roughly estimated by using the Roberta model. Then the Markov chain model is used to evaluate the sentences in a fine-grained manner. Our team won the first place in overall performance, with the fourth place in MAS task, the seventh place in RRS task and the eleventh place in QS task. For the QS and RRS tasks, we investigate the performanceS of the end-to-end pre-trained seq2seq model. Experiments show that the methods of adversarial training and reverse translation are beneficial to improve the fine tuning performance.
{"title":"ChicHealth @ MEDIQA 2021: Exploring the limits of pre-trained seq2seq models for medical summarization","authors":"Liwen Xu, Yan Zhang, Lei Hong, Yi Cai, Szui Sung","doi":"10.18653/v1/2021.bionlp-1.29","DOIUrl":"https://doi.org/10.18653/v1/2021.bionlp-1.29","url":null,"abstract":"In this article, we will describe our system for MEDIQA2021 shared tasks. First, we will describe the method of the second task, multiple answer summary (MAS). For extracting abstracts, we follow the rules of (CITATION). First, the candidate sentences are roughly estimated by using the Roberta model. Then the Markov chain model is used to evaluate the sentences in a fine-grained manner. Our team won the first place in overall performance, with the fourth place in MAS task, the seventh place in RRS task and the eleventh place in QS task. For the QS and RRS tasks, we investigate the performanceS of the end-to-end pre-trained seq2seq model. Experiments show that the methods of adversarial training and reverse translation are beneficial to improve the fine tuning performance.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116362200","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.bionlp-1.2
Jiarun Cao, Niels Peek, A. Renehan, S. Ananiadou
Automatically identifying genetic mutations in the cancer literature using text mining technology has been an important way to study the vast amount of cancer medical literature. However, novel knowledge regarding the genetic variants proliferates rapidly, though current supervised learning models struggle with discovering these unknown entity types. Few-shot learning allows a model to perform effectively with great generalization on new entity types, which has not been explored in recognizing cancer mutation detection. This paper addresses cancer mutation detection tasks with few-shot learning paradigms. We propose GDPN framework, which models the label dependency from the training examples in the support set and approximates the transition scores via Gaussian distribution. The experiments on three benchmark cancer mutation datasets show the effectiveness of our proposed model.
{"title":"Gaussian Distributed Prototypical Network for Few-shot Genomic Variant Detection","authors":"Jiarun Cao, Niels Peek, A. Renehan, S. Ananiadou","doi":"10.18653/v1/2023.bionlp-1.2","DOIUrl":"https://doi.org/10.18653/v1/2023.bionlp-1.2","url":null,"abstract":"Automatically identifying genetic mutations in the cancer literature using text mining technology has been an important way to study the vast amount of cancer medical literature. However, novel knowledge regarding the genetic variants proliferates rapidly, though current supervised learning models struggle with discovering these unknown entity types. Few-shot learning allows a model to perform effectively with great generalization on new entity types, which has not been explored in recognizing cancer mutation detection. This paper addresses cancer mutation detection tasks with few-shot learning paradigms. We propose GDPN framework, which models the label dependency from the training examples in the support set and approximates the transition scores via Gaussian distribution. The experiments on three benchmark cancer mutation datasets show the effectiveness of our proposed model.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"48 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114010328","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}
Event detection from clinical notes has been traditionally solved with rule based and statistical natural language processing (NLP) approaches that require extensive domain knowledge and feature engineering. In this paper, we have explored the feasibility of approaching this task with recurrent neural networks, clinical word embeddings and introduced a hybrid architecture to improve detection for entities with smaller representation in the dataset. A comparative analysis is also done which reveals the complementary behavior of neural networks and conditional random fields in clinical entity detection.
{"title":"Clinical Event Detection with Hybrid Neural Architecture","authors":"A. Maharana, Meliha Yetisgen-Yildiz","doi":"10.18653/v1/W17-2345","DOIUrl":"https://doi.org/10.18653/v1/W17-2345","url":null,"abstract":"Event detection from clinical notes has been traditionally solved with rule based and statistical natural language processing (NLP) approaches that require extensive domain knowledge and feature engineering. In this paper, we have explored the feasibility of approaching this task with recurrent neural networks, clinical word embeddings and introduced a hybrid architecture to improve detection for entities with smaller representation in the dataset. A comparative analysis is also done which reveals the complementary behavior of neural networks and conditional random fields in clinical entity detection.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128133190","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}
We propose a novel, Abstract Meaning Representation (AMR) based approach to identifying molecular events/interactions in biomedical text. Our key contributions are: (1) an empirical validation of our hypothesis that an event is a subgraph of the AMR graph, (2) a neural network-based model that identifies such an event subgraph given an AMR, and (3) a distant supervision based approach to gather additional training data. We evaluate our approach on the 2013 Genia Event Extraction dataset and show promising results.
{"title":"Biomedical Event Extraction using Abstract Meaning Representation","authors":"Sudha Rao, D. Marcu, Kevin Knight, Hal Daumé","doi":"10.18653/v1/W17-2315","DOIUrl":"https://doi.org/10.18653/v1/W17-2315","url":null,"abstract":"We propose a novel, Abstract Meaning Representation (AMR) based approach to identifying molecular events/interactions in biomedical text. Our key contributions are: (1) an empirical validation of our hypothesis that an event is a subgraph of the AMR graph, (2) a neural network-based model that identifies such an event subgraph given an AMR, and (3) a distant supervision based approach to gather additional training data. We evaluate our approach on the 2013 Genia Event Extraction dataset and show promising results.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121943969","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.bionlp-1.36
Kevin Xie, B. Litt, D. Roth, C. Ellis
A wealth of important clinical information lies untouched in the Electronic Health Record, often in the form of unstructured textual documents. For patients with Epilepsy, such information includes outcome measures like Seizure Frequency and Dates of Last Seizure, key parameters that guide all therapy for these patients. Transformer models have been able to extract such outcome measures from unstructured clinical note text as sentences with human-like accuracy; however, these sentences are not yet usable in a quantitative analysis for large-scale studies. In this study, we developed a pipeline to quantify these outcome measures. We used text summarization models to convert unstructured sentences into specific formats, and then employed rules-based quantifiers to calculate seizure frequencies and dates of last seizure. We demonstrated that our pipeline of models does not excessively propagate errors and we analyzed its mistakes. We anticipate that our methods can be generalized outside of epilepsy to other disorders to drive large-scale clinical research.
{"title":"Quantifying Clinical Outcome Measures in Patients with Epilepsy Using the Electronic Health Record","authors":"Kevin Xie, B. Litt, D. Roth, C. Ellis","doi":"10.18653/v1/2022.bionlp-1.36","DOIUrl":"https://doi.org/10.18653/v1/2022.bionlp-1.36","url":null,"abstract":"A wealth of important clinical information lies untouched in the Electronic Health Record, often in the form of unstructured textual documents. For patients with Epilepsy, such information includes outcome measures like Seizure Frequency and Dates of Last Seizure, key parameters that guide all therapy for these patients. Transformer models have been able to extract such outcome measures from unstructured clinical note text as sentences with human-like accuracy; however, these sentences are not yet usable in a quantitative analysis for large-scale studies. In this study, we developed a pipeline to quantify these outcome measures. We used text summarization models to convert unstructured sentences into specific formats, and then employed rules-based quantifiers to calculate seizure frequencies and dates of last seizure. We demonstrated that our pipeline of models does not excessively propagate errors and we analyzed its mistakes. We anticipate that our methods can be generalized outside of epilepsy to other disorders to drive large-scale clinical research.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134155279","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}
Andre Lamurias, M. J. Rodrigues, L. Clarke, Francisco M. Couto
This paper describes our system to extract binary regulatory relations from text, used to participate in the SeeDev task of BioNLP-ST 2016. Our system was based on machine learning, using support vector machines with a shallow linguistic kernel to identify each type of relation. Additionally, we employed a distant supervised approach to increase the size of the training data. Our submission obtained the third best precision of the SeeDev-binary task. Although the distant supervised approach did not significantly improve the results, we expect that by exploring other techniques to use unlabeled data should lead to better results.
{"title":"Extraction of Regulatory Events using Kernel-based Classifiers and Distant Supervision","authors":"Andre Lamurias, M. J. Rodrigues, L. Clarke, Francisco M. Couto","doi":"10.18653/v1/W16-3011","DOIUrl":"https://doi.org/10.18653/v1/W16-3011","url":null,"abstract":"This paper describes our system to extract binary regulatory relations from text, used to participate in the SeeDev task of BioNLP-ST 2016. Our system was based on machine learning, using support vector machines with a shallow linguistic kernel to identify each type of relation. Additionally, we employed a distant supervised approach to increase the size of the training data. Our submission obtained the third best precision of the SeeDev-binary task. Although the distant supervised approach did not significantly improve the results, we expect that by exploring other techniques to use unlabeled data should lead to better results.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130764876","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.bionlp-1.36
Ryuki Ida, Makoto Miwa, Yutaka Sasaki
This paper proposes a new document classification method that incorporates the representations of a literature graph created from bibliographic and entity information.Recently, document classification performance has been significantly improved with large pre-trained language models; however, there still remain documents that are difficult to classify. External information, such as bibliographic information, citation links, descriptions of entities, and medical taxonomies, has been considered one of the keys to dealing with such documents in document classification. Although several document classification methods using external information have been proposed, they only consider limited relationships, e.g., word co-occurrence and citation relationships. However, there are multiple types of external information.To overcome the limitation of the conventional use of external information, we propose a document classification model that simultaneously considers bibliographic and entity information to deeply model the relationships among documents using the representations of the literature graph.The experimental results show that our proposed method outperforms existing methods on two document classification datasets in the biomedical domain with the help of the literature graph.
{"title":"Biomedical Document Classification with Literature Graph Representations of Bibliographies and Entities","authors":"Ryuki Ida, Makoto Miwa, Yutaka Sasaki","doi":"10.18653/v1/2023.bionlp-1.36","DOIUrl":"https://doi.org/10.18653/v1/2023.bionlp-1.36","url":null,"abstract":"This paper proposes a new document classification method that incorporates the representations of a literature graph created from bibliographic and entity information.Recently, document classification performance has been significantly improved with large pre-trained language models; however, there still remain documents that are difficult to classify. External information, such as bibliographic information, citation links, descriptions of entities, and medical taxonomies, has been considered one of the keys to dealing with such documents in document classification. Although several document classification methods using external information have been proposed, they only consider limited relationships, e.g., word co-occurrence and citation relationships. However, there are multiple types of external information.To overcome the limitation of the conventional use of external information, we propose a document classification model that simultaneously considers bibliographic and entity information to deeply model the relationships among documents using the representations of the literature graph.The experimental results show that our proposed method outperforms existing methods on two document classification datasets in the biomedical domain with the help of the literature graph.","PeriodicalId":200974,"journal":{"name":"Workshop on Biomedical Natural Language Processing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130746137","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：