Statistical principle-based approach for gene and protein related object recognition

Lai, Po Ting; Huang, Ming; Yang, Ting; Hsu, Wen Lian; Tsai, Richard Tzong Han

doi:10.1186/s13321-018-0314-7

Cited by 7 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in the process of template matching, the scoring mechanism assigns scores according to the relations between matched/unmatched units, insertions/deletions, and the corresponding unit. We adopted logistic regression (LR) (Ng, 2004) to determine whether a template is activated by a sequence pattern since the LR‐based model is efficient in learning the weight of a template for the task of recognizing objects in a text sequence (Lai, Huang, Yang, Hsu, & Tsai, 2018; Lee & Liu, 2003; Liang & Forbus, 2015). The similarity of an alignment of template t and labeled pattern l is calculated by the following formula:

normalS ((), normalt, normall) = \sum_{i} λ_{M} ((), the normali - th matched word) + \sum_{j} λ_{D} ((), the normalj - th deletion) + \sum_{k} λ_{I} ((), the normalk - th inserted bigram),

where λ M is the weight of the matched words, λ D is the weight of deleted units, and λ I is the weight of the bigram consisting of the insertion and its neighboring left (resp.…”

Section: Methodsmentioning

confidence: 99%

A flexible template generation and matching method with applications for publication reference metadata extraction

Yang

Hsieh

Liu

et al. 2020

Asso for Info Science & Tech

View full text Add to dashboard Cite

Conventional rule‐based approaches use exact template matching to capture linguistic information and necessarily need to enumerate all variations. We propose a novel flexible template generation and matching scheme called the principle‐based approach (PBA) based on sequence alignment, and employ it for reference metadata extraction (RME) to demonstrate its effectiveness. The main contributions of this research are threefold. First, we propose an automatic template generation that can capture prominent patterns using the dominating set algorithm. Second, we devise an alignment‐based template‐matching technique that uses a logistic regression model, which makes it more general and flexible than pure rule‐based approaches. Last, we apply PBA to RME on extensive cross‐domain corpora and demonstrate its robustness and generality. Experiments reveal that the same set of templates produced by the PBA framework not only deliver consistent performance on various unseen domains, but also surpass hand‐crafted knowledge (templates). We use four independent journal style test sets and one conference style test set in the experiments. When compared to renowned machine learning methods, such as conditional random fields (CRF), as well as recent deep learning methods (i.e., bi‐directional long short‐term memory with a CRF layer, Bi‐LSTM‐CRF), PBA has the best performance for all datasets.

show abstract

normalS ((), normalt, normall) = \sum_{i} λ_{M} ((), the normali - th matched word) + \sum_{j} λ_{D} ((), the normalj - th deletion) + \sum_{k} λ_{I} ((), the normalk - th inserted bigram),

where λ M is the weight of the matched words, λ D is the weight of deleted units, and λ I is the weight of the bigram consisting of the insertion and its neighboring left (resp.…”

Section: Methodsmentioning

confidence: 99%

A flexible template generation and matching method with applications for publication reference metadata extraction

Yang

Hsieh

Liu

et al. 2020

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…In the NER stage, BelSmile consists of an ensemble system composed of three approaches: statistical principle, conditional random fields (CRF) and dictionary-based. The statistical principle-based approach is used to identify protein mentions and achieved the highest score in terms of the second evaluation metric of the BioCreative V.5 Gene and protein related object recognition (GPRO) task (20). The CRF-based NERChem (21) is used to identify chemical mentions.…”

Section: Methodsmentioning

confidence: 99%

The extraction of complex relationships and their conversion to biological expression language (BEL) overview of the BioCreative VI (2017) BEL track

et al. 2019

Self Cite

View full text Add to dashboard Cite

Knowledge of the molecular interactions of biological and chemical entities and their involvement in biological processes or clinical phenotypes is important for data interpretation. Unfortunately, this knowledge is mostly embedded in the literature in such a way that it is unavailable for automated data analysis procedures. Biological expression language (BEL) is a syntax representation allowing for the structured representation of a broad range of biological relationships. It is used in various situations to extract such knowledge and transform it into BEL networks. To support the tedious and time-intensive extraction work of curators with automated methods, we developed the BEL track within the framework of BioCreative Challenges. Within the BEL track, we provide training data and an evaluation environment to encourage the text mining community to tackle the automatic extraction of complex BEL relationships. In 2017 BioCreative VI, the 2015 BEL track was repeated with new test data. Although only minor improvements in text snippet retrieval for given statements were achieved during this second BEL task iteration, a significant increase of BEL statement extraction performance from provided sentences could be seen. The best performing system reached a 32% F-score for the extraction of complete BEL statements and with the given named entities this increased to 49%. This time, besides rule-based systems, new methods involving hierarchical sequence labeling and neural networks were applied for BEL statement extraction.

show abstract

“…For example, Po-Ting Lai et al introduced the statistical principlebased approach (SPBA) for named entity recognition and participated in a Bio-Creative V.5 gene-and protein-related object (GPRO) task to evaluate the ability of SPBA for processing patent abstracts. In Bio-Creative V.5 GPRO task, this approach achieved an F-score of 73.73% on GPRO type 1 and an F-score of 78.66% on combining GPRO type 1 and 2 [22]. However, most statistics-based named entity recognition models have high training time complexity, high training cost, and strong dependence on the quality of corpus.…”

Section: Related Workmentioning

confidence: 99%

A Study on Standardization of Security Evaluation Information for Chemical Processes Based on Deep Learning

Peng¹,

Gao²,

Bai³

2021

Processes

View full text Add to dashboard Cite

Hazard and operability analysis (HAZOP) is one of the most commonly used hazard analysis methods in the petrochemical industry. The large amount of unstructured data in HAZOP reports has generated an information explosion which has led to a pressing need for technologies that can simplify the use of this information. In order to solve the problem that massive data are difficult to reuse and share, in this study, we propose a new deep learning framework for Chinese HAZOP documents to perform a named entity recognition (NER) task, aiming at the characteristics of HAZOP documents, such as polysemy, multi-entity nesting, and long-distance text. Specifically, the preprocessed data are input into an embeddings from language models (ELMo) and a double convolutional neural network (DCNN) model to extract rich character features. Meanwhile, a bidirectional long short-term memory (BiLSTM) network is used to extract long-distance semantic information. Finally, the results are decoded by a conditional random field (CRF), and then output. Experiments were carried out using the HAZOP report of a coal seam indirect liquefaction project. The experimental results for the proposed model showed that the accuracy rate of the optimal results reached 90.83, the recall rate reached 92.46, and the F-value reached the highest 91.76%, which was significantly improved as compared with other models.

show abstract

Statistical principle-based approach for gene and protein related object recognition

Cited by 7 publications

References 14 publications

A flexible template generation and matching method with applications for publication reference metadata extraction

A flexible template generation and matching method with applications for publication reference metadata extraction

The extraction of complex relationships and their conversion to biological expression language (BEL) overview of the BioCreative VI (2017) BEL track

A Study on Standardization of Security Evaluation Information for Chemical Processes Based on Deep Learning

Contact Info

Product

Resources

About