Tree Kernel-based Protein-Protein Interaction Extraction Considering both Modal Verb Phrases and Appositive Dependency Features

Ma, Changlin; Zhang, Yong; Zhang, Maoyuan

doi:10.1145/2740908.2741705

Cited by 6 publications

(15 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By the way, the Composite kernel version equipped with simplification rules improved F1-measure in almost 4 points compared to its previous version reported in [Miwa et al, 2009]. Moreover, although the Composite kernel had obtained the overall highest scores on the IEPA corpus, this kernel has high computation complexity and difficulty in implementation [Ma et al, 2015].…”

Section: Comparative Cross-validation Evaluationmentioning

confidence: 88%

“…4 were taken from Quian and Zhou (2012). However, in [Ma et al, 2015], the authors reported an improvement of 1,2% percentage points in F1 over the SDP-CPT kernel results with their enhanced EOEP-CPT kernel. The main reason for such an improvement, according to the authors, is due to the fact that EOEP-CPT algorithm is more precise and concise than the SDP-CPT when both kernels uses the same version of the Stanford parser (v2.0.4).…”

Section: Comparative Cross-validation Evaluationmentioning

confidence: 96%

“…Tree-based kernels are based on common substructures containing two entities in order to implicitly exploit structured features by directly computing the similarity between two trees, as it is done in [Culotta and Sorensen, 2004] ] [Quian & Zhou, 2012 [Ma et al, 2015]. Tree-based kernels explore various structured feature spaces by processing parsing trees in order to capture syntactically structured information from the examples.…”

Section: Kernel-based Approaches To Rementioning

confidence: 99%

“… EOEP-CPT [Ma et al, 2015]. The Effective Optimization and Expanding Path-directed Constituent Parse Tree (EOEP-CPT) [Ma et al, 2015] kernel is an improvement over the SDP-CPT kernel.…”

Section: Selected Re Systems For Comparisonmentioning

confidence: 99%

“…4 summarizes the results where the highest scores for F1-measure are in bold, and the best AUC scores in italics. kBSPS [Tikk et al, 2010] Composite [Miwa et al, 2010] SDP-CPT [Quian & Zhou, 2012] EOEP-CPT [Ma et al, 2015 The overall results in Tab. 4 show that SDP-CPT had the best performance on the LLL dataset in terms of F1-measure.…”

Section: Comparative Cross-validation Evaluationmentioning

confidence: 99%

See 4 more Smart Citations

A logic-based relational learning approach to relation extraction: The OntoILPER system

Lima

Espinasse

Freitas

2019

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Relation Extraction (RE), the task of detecting and characterizing semantic relations between entities in text, has gained much importance in the last two decades, mainly in the biomedical domain. Many papers have been published on Relation Extraction using supervised machine learning techniques. Most of these techniques rely on statistical methods, such as feature-based and tree-kernels-based methods. Such statistical learning techniques are usually based on a propositional hypothesis space for representing examples, i.e., they employ an attribute-value representation of features. This kind of representation has some drawbacks, particularly in the extraction of complex relations which demand more contextual information about the involving instances, i.e., it is not able to effectively capture structural information from parse trees without loss of information. In this work, we present OntoILPER, a logic-based relational learning approach to Relation Extraction that uses Inductive Logic Programming for generating extraction models in the form of symbolic extraction rules. OntoILPER takes profit of a rich relational representation of examples, which can alleviate the aforementioned drawbacks. The proposed relational approach seems to be more suitable for Relation Extraction than statistical ones for several reasons that we argue. Moreover, OntoILPER uses a domain ontology that guides the background knowledge generation process and is used for storing the extracted relation instances. The induced extraction rules were evaluated on three protein-protein interaction datasets from the biomedical domain. The performance of OntoILPER extraction models was compared with other state-of-the-art RE systems. The encouraging results seem to demonstrate the effectiveness of the proposed solution.

show abstract

Section: Comparative Cross-validation Evaluationmentioning

confidence: 88%

Section: Comparative Cross-validation Evaluationmentioning

confidence: 96%

Section: Kernel-based Approaches To Rementioning

confidence: 99%

“… EOEP-CPT [Ma et al, 2015]. The Effective Optimization and Expanding Path-directed Constituent Parse Tree (EOEP-CPT) [Ma et al, 2015] kernel is an improvement over the SDP-CPT kernel.…”

Section: Selected Re Systems For Comparisonmentioning

confidence: 99%

Section: Comparative Cross-validation Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

A logic-based relational learning approach to relation extraction: The OntoILPER system

Lima

Espinasse

Freitas

2019

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

Translating cancer genomics into precision medicine with artificial intelligence: applications, challenges and future perspectives

et al. 2019

View full text Add to dashboard Cite

In the field of cancer genomics, the broad availability of genetic information offered by next-generation sequencing technologies and rapid growth in biomedical publication has led to the advent of the big-data era. Integration of artificial intelligence (AI) approaches such as machine learning, deep learning, and natural language processing (NLP) to tackle the challenges of scalability and high dimensionality of data and to transform big data into clinically actionable knowledge is expanding and becoming the foundation of precision medicine. In this paper, we review the current status and future directions of AI application in cancer genomics within the context of workflows to integrate genomic analysis for precision cancer care. The existing solutions of AI and their limitations in cancer genetic testing and diagnostics such as variant calling and interpretation are critically analyzed. Publicly available tools or algorithms for key NLP technologies in the literature mining for evidence-based clinical recommendations are reviewed and compared. In addition, the present paper highlights the challenges to AI adoption in digital healthcare with regard to data requirements, algorithmic transparency, reproducibility, and real-world assessment, and discusses the importance of preparing patients and physicians for modern digitized healthcare. We believe that AI will remain the main driver to healthcare transformation toward precision medicine, yet the unprecedented challenges posed should be addressed to ensure safety and beneficial impact to healthcare.

show abstract

Protein-protein interaction relation extraction based on multigranularity semantic fusion

Li¹,

Chen²,

Qin³

et al. 2021

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Tree Kernel-based Protein-Protein Interaction Extraction Considering both Modal Verb Phrases and Appositive Dependency Features

Cited by 6 publications

References 25 publications

A logic-based relational learning approach to relation extraction: The OntoILPER system

A logic-based relational learning approach to relation extraction: The OntoILPER system

Translating cancer genomics into precision medicine with artificial intelligence: applications, challenges and future perspectives

Protein-protein interaction relation extraction based on multigranularity semantic fusion

Contact Info

Product

Resources

About