A transition-based joint model for disease named entity recognition and normalization

Lou, Yinxia; Zhang, Yue; Qian, Tao; Li, Fēi; Xiong, Shufeng

doi:10.1093/bioinformatics/btx172

Cited by 59 publications

(49 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interesting though are differences for the same approach on different evaluation data sets. For the second-best system by Sachan et al [47], F 1 scores differ for BC5CDR and NCBI by 2.0 (for the third-best [46] by 2.7) percentage points, whereas for the best non-DL approach by Lou et al [48], this difference amounts to remarkable 4.1 percentage points. This hints at a strong dependence of the results of the same system set-up on the specific corpus these results have been worked out and, thus, limits generalizability.…”

Section: Medical Information Extraction In the Age Of Deep Learningmentioning

confidence: 99%

“…Lee et al [20] Sachan et al [47] Wang et al [46] Xu et al [49] Hong and Lee [51] Beltagy et al [19] Xu et al [49] Zhao et al [39] Zhao et al [39] Sachan et al [47] Lee et al [20] Hong and Lee [51] Lou et al [48] Wang et al [46] Lou et al [48] Corpus BioBERT v1.1 [20]: self-trained BERT on PubMed pre-trained embeddings + self-trained on PubMed pre-trained: [16] word embeddings [50] self-trained on PubMed and PMC pre-trained word embeddings (PubMed): [16,52] SciBERT [19]: self-trained BERT on biomedical full texts from Semantic Scholar word embeddings [50] self-trained on PubMed and PMC pre-trained: [16,[53][54][55] pre-trained: [16,[53][54][55] pre-trained embeddings + self-trained on PubMed BioBERT V1.1 [20]: self-trained BERT on PubMed pre-trained word embeddings (PubMed): [16,52] n/a pre-trained: [16] n/a…”

Section: Citationsmentioning

confidence: 99%

See 1 more Smart Citation

Medical Information Extraction in the Age of Deep Learning

Hahn

Oleynik

2020

Yearb Med Inform

View full text Add to dashboard Cite

Objectives: We survey recent developments in medical Information Extraction (IE) as reported in the literature from the past three years. Our focus is on the fundamental methodological paradigm shift from standard Machine Learning (ML) techniques to Deep Neural Networks (DNNs). We describe applications of this new paradigm concentrating on two basic IE tasks, named entity recognition and relation extraction, for two selected semantic classes—diseases and drugs (or medications)—and relations between them. Methods: For the time period from 2017 to early 2020, we searched for relevant publications from three major scientific communities: medicine and medical informatics, natural language processing, as well as neural networks and artificial intelligence. Results: In the past decade, the field of Natural Language Processing (NLP) has undergone a profound methodological shift from symbolic to distributed representations based on the paradigm of Deep Learning (DL). Meanwhile, this trend is, although with some delay, also reflected in the medical NLP community. In the reporting period, overwhelming experimental evidence has been gathered, as illustrated in this survey for medical IE, that DL-based approaches outperform non-DL ones by often large margins. Still, small-sized and access-limited corpora create intrinsic problems for data-greedy DL as do special linguistic phenomena of medical sublanguages that have to be overcome by adaptive learning strategies. Conclusions: The paradigm shift from (feature-engineered) ML to DNNs changes the fundamental methodological rules of the game for medical NLP. This change is by no means restricted to medical IE but should also deeply influence other areas of medical informatics, either NLP- or non-NLP-based.

show abstract

Section: Medical Information Extraction In the Age Of Deep Learningmentioning

confidence: 99%

Section: Citationsmentioning

confidence: 99%

Medical Information Extraction in the Age of Deep Learning

Hahn

Oleynik

2020

Yearb Med Inform

View full text Add to dashboard Cite

show abstract

“…The first model uses a separate transition system for each level in the hierarchy and enforces nesting constraints to produce non-overlapping structures. The transition system used in this model allows us to construct representations of multi-word segments which have been shown to be essential for multi-word annotations such as NER and chunking ( [7], [9], [10] and [11]). We will refer to this model as the Multitask Shift-Reduce (MT-SR for short) system.…”

Section: Transition-based Slot Fillingmentioning

confidence: 99%

Neural Transition Systems for Modeling Hierarchical Semantic Representations

et al. 2019

View full text Add to dashboard Cite

While virtual agents are becoming ubiquitous in our daily life, their functionality is limited to simple commands which involve a single intent and an unstructured set of entities. Typically, in such systems, the natural language understanding (NLU) component uses a sequence tagging model to extract a flat meaning representation. However, in order to support complex user requests with multiple intents with their associated entities, such as those in a product ordering domain, a structured semantic representation is necessary. In this paper, we present hierarchical semantic representations for product ordering in the food services domain and two NLU models that produce such representations efficiently using deep neural networks. The models are based on transition-based algorithms which have been proven to be effective and scalable for multiple NLP tasks such as syntactic parsing and slot filling. The first model uses a multitasking architecture containing multiple transition systems with tree constraints to model the hierarchical annotations, while the second model treats the task as a constituency parsing problem by mapping the target domain annotations to a constituency tree. We demonstrate that both multi-task and constituencybased transition systems achieve competitive results and even show improvements over sequential models, showing their effectiveness in modeling hierarchical structure.

show abstract

“…normalization. Lou et al (2017) proposed a transition-based model to jointly perform medical named entity recognition and normalization, casting the output construction process into an incremental state transition process. However, these existing joint modeling methods (1) rely heavily on handcrafted features and task specific resources thus fail to encode complicated and general features such as characterlevel and semantic-level features; (2) use simplistic ways to jointly model medical named entity recognition and normalization, which cannot provide essential mutual supports between these two.…”

Section: Introductionmentioning

confidence: 99%

A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization

Zhao

Liu

Zhao

et al. 2019

AAAI

107

View full text Add to dashboard Cite

State-of-the-art studies have demonstrated the superiority of joint modeling over pipeline implementation for medical named entity recognition and normalization due to the mutual benefits between the two processes. To exploit these benefits in a more sophisticated way, we propose a novel deep neural multi-task learning framework with explicit feedback strategies to jointly model recognition and normalization. On one hand, our method benefits from the general representations of both tasks provided by multi-task learning. On the other hand, our method successfully converts hierarchical tasks into a parallel multi-task setting while maintaining the mutual supports between tasks. Both of these aspects improve the model performance. Experimental results demonstrate that our method performs significantly better than state-of-theart approaches on two publicly available medical literature datasets.

show abstract

A transition-based joint model for disease named entity recognition and normalization

Abstract: dhji@whu.edu.cn.

Cited by 59 publications

References 9 publications

Medical Information Extraction in the Age of Deep Learning

Medical Information Extraction in the Age of Deep Learning

Neural Transition Systems for Modeling Hierarchical Semantic Representations

A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization

Contact Info

Product

Resources

About