An Attentive Neural Sequence Labeling Model for Adverse Drug Reactions Mentions Extraction

Ding, Peng; Zhou, Xiaobing; Zhang, Xuejie; Wang, Jin; Lei, Zhenfeng

doi:10.1109/access.2018.2882443

Cited by 21 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conduct experiments to examine the effectiveness of CNN-NEAT’s Attention in locating the text segments containing the correct side effects. We benchmark our results against a lexicon-based tagging using UMLS thesaurus for medical terms [ 52 ] and a state-of-the-art neural side effect extractor [ 21 ] which was supervisedly trained to identify side effect mentions in social media contents. In this task, correctly predicting the positive side effects is of the utmost importance, hence, we benchmark the text segments extracted from CNN-NEAT’s Attention against two mentioned baselines on precision metric.…”

Section: Resultsmentioning

confidence: 99%

“…By learning to focus on essential text segments, attention allows text encoders to capture long term semantic dependencies with regard to auxiliary contextual information [ 41 , 42 ]. In our related task of ADR mentions extraction, attention has been adopted recently in neural sequence labelling models [ 21 , 43 ], resulting in promising improvement. Inspired by the concept, we enhance text encoding with user expertise attention.…”

Section: Methodsmentioning

confidence: 99%

“…ADR mining systems typically include a named entity recognition (NER) model and a relationship or semantic role labeling model [ 19 , 20 ]. Recent neural approaches address lexical variation in user-generated content – the difficulty faced by traditional keyword matching and rule-based approaches – to improve recognition and labeling components [ 21 , 22 ]. Distributed word representations [ 23 , 24 ] constructed from context can capture semantics based on the hypothesis that synonyms often share similar contextual words.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Neural side effect discovery from user credibility and experience-assessed online health discussions

et al. 2020

View full text Add to dashboard Cite

Background Health 2.0 allows patients and caregivers to conveniently seek medical information and advice via e-portals and online discussion forums, especially regarding potential drug side effects. Although online health communities are helpful platforms for obtaining non-professional opinions, they pose risks in communicating unreliable and insufficient information in terms of quality and quantity. Existing methods in extracting user-reported adverse drug reactions (ADRs) in online health forums are not only insufficiently accurate as they disregard user credibility and drug experience, but are also expensive as they rely on supervised ground truth annotation of individual statement. We propose a NEural ArchiTecture for Drug side effect prediction (NEAT), which is optimized on the task of drug side effect discovery based on a complete discussion while being attentive to user credibility and experience, thus, addressing the mentioned shortcomings. We train our neural model in a self-supervised fashion using ground truth drug side effects from mayoclinic.org. NEAT learns to assign each user a score that is descriptive of their credibility and highlights the critical textual segments of their post. Results Experiments show that NEAT improves drug side effect discovery from online health discussion by 3.04 % from user-credibility agnostic baselines, and by 9.94 % from non-neural baselines in term of F 1 . Additionally, the latent credibility scores learned by the model correlate well with trustworthiness signals, such as the number of “thanks” received by other forum members, and improve credibility heuristics such as number of posts by 0.113 in term of Spearman’s rank correlation coefficient. Experience-based self-supervised attention highlights critical phrases such as mentioned side effects, and enhances fully supervised ADR extraction models based on sequence labelling by 5.502 % in terms of precision. Conclusions NEAT considers both user credibility and experience in online health forums, making feasible a self-supervised approach to side effect prediction for mentioned drugs. The derived user credibility and attention mechanism are transferable and improve downstream ADR extraction models. Our approach enhances automatic drug side effect discovery and fosters research in several domains including pharmacovigilance and clinical studies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Neural side effect discovery from user credibility and experience-assessed online health discussions

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Zheng [37] proposed the Opentag model, using BiLSTM to capture context information and CRF to complete sequence labeling, which is a new attention mechanism to provide interpretation for model decision-making. Similarly, the sequence labeling task is also widely used in the medical field [6], [11], [29], [32].…”

Section: Related Workmentioning

confidence: 99%

Information Extraction for Intestinal Cancer Electronic Medical Records

et al. 2020

View full text Add to dashboard Cite

The data generated by the structured electronic medical records is helpful for mining and extracting medical data, and it is an effective way to make effective use of valuable data resources. However, the hospitals have accumulated a large number of unstructured data in electronic medical records, which cannot be effectively searched, resulting in serious waste of resources. In this paper, we study the problem of extracting attribute values from the unstructured text in electronic medical records. By observing intestinal cancer diagnostic texts, our attributes have two categories-discriminative attributes and extractive attributes, which use the text classification and the sequence labeling to tackle attribute values extraction problems. For discriminative attributes, we firstly divide the text into sentences/segments as instances. Secondly, we finetune the pre-trained word embedding to capture domain-specific semantics/knowledge. Thirdly, we also use an attention mechanism to select the most important instance for different attribute extractors. Finally, multi-tasking learning is used to share useful information to get better experimental results. For extractive attributes, we propose a novel model to get attribute values, including the BiLSTM layer, the CNN layer and the CRF layer. In particular, we use BiLSTM and CNN to learn text features and CRF as the last layer of the model. Experiments have shown that our method is superior to several competitive baseline methods.

show abstract

“…TF-IDF) and syntactic features. Recently, deep learning has been widely used in natural language processing (NLP) [12]- [15], and it brings hope to reduce manual feature engineering in various tasks. Compare with hand-designed features and traditional discrete feature representation, it provides a different way to automatically learn dense features representation for text, such as words, phrases and sentences.…”

Section: Introductionmentioning

confidence: 99%

Keyphrase Generation With CopyNet and Semantic Web

Zhu

Lyu

2020

IEEE Access

View full text Add to dashboard Cite

Keyphrases provide core information for users to understand the document. Most previous works utilize machine learning based methods for keyphrases extraction and achieve promising performance. However, these methods focus on identify keyphrases from the input text, and can not extract keyphrases that do not appear in the text. In this paper, we present an encoder-decoder framework, which incorporating copying mechanism, to generate keyphrases for the given text. This framework (CopyNet) integrates the generation part and copying part. The generation part generates the keyphrase from the predefined vocabulary, and the copy part gets the keyphrases from the source text. Furthermore, we improve the CopyNet by using different probability of the two parts. To incorporate more related information for keyphrase generation, the automatically built keyphrase semantic web is merged into the dataset to participate in the training process of the neural network. Semantic similarity based and word co-occurrence based methods are used for keyphrase semantic web construction. We build a large-scale biomedical keyphrase dataset to evaluate the system performance. Experiments show that our improved CopyNet can achieve better performance with different portions of the generation and copying part, and the incorporation of the semantic web also effectively improves the keyphrase generation. INDEX TERMS Keyphrase generation, encoder-decoder model, copying mechanism, semantic web.

show abstract

An Attentive Neural Sequence Labeling Model for Adverse Drug Reactions Mentions Extraction

Cited by 21 publications

References 27 publications

Neural side effect discovery from user credibility and experience-assessed online health discussions

Neural side effect discovery from user credibility and experience-assessed online health discussions

Information Extraction for Intestinal Cancer Electronic Medical Records

Keyphrase Generation With CopyNet and Semantic Web

Contact Info

Product

Resources

About