Semantic relation extraction aware of N-gram features from unstructured biomedical text

Wang, Zheng; Xu, Shuo; Zhu, Liehuang

doi:10.1016/j.jbi.2018.08.011

Cited by 16 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xu et al [42] merged the idea of learning-to-rank into the textual information retrieval for query expansion. Wang et al [40] proposed Rel-TNG and Type-TNG models, which were combined with Rel-LDA and Type-LDA for semantic relation retrieval from biomedical documents. In deep learning-based methods, the basic ideas include transformer [10], Convolutional Neural Networks (CNN) [23], transfer learning [23][29], Graph Convolutional Network [39] and so on.…”

Section: B Biomedical Text Information Retrievalmentioning

confidence: 99%

Effective Natural Language Processing and Interpretable Machine Learning for Structuring CT Liver-Tumor Reports

Chuang

Han

et al. 2022

IEEE Access

View full text Add to dashboard Cite

In the past, the liver tumors were reported manually in an unstructured format. There actually exists much valuable knowledge in these reports for further disease risk assessment, disease recognition and treatment recommendation. Yet, it is not easy to read and mine knowledge from the unstructured reports. Hence, how to extract the knowledge from these biomedical reports effectively and efficiently has been a challenging issue in the past decades. Although a set of Natural Language Processing techniques were proposed for Bio-medical information retrieval, few related works were made on transforming the unstructured CT liver-tumor reports into structured ones. To aim at this issue, in this paper, we propose a two-stage report structuring method by integrating effective Natural Language Processing (NLP) and interpretable machine learning. For the first stage, the candidate keywords in unstructured reports are extracted. Next, the feature keywords are determined by the feature-selection technique. For the second stage, the well-known multi-classifiers are performed, and finally the reports are labeled in a refined structure format. Further, the factor keywords in the classification model are filtered to interpret the performance. In overall, the proposed report structuring method generates a hierarchical data structure, including the common features and refined features in the 1 st and 2 nd levels/stages, respectively. To reveal the performance of proposed method, a set of evaluations were conducted and the results show that, the proposed method is more promising than the fashion neural networks such as Bert (Bidirectional Encoder Representations from Transformers) in terms of effectiveness and efficiency.

show abstract

Section: B Biomedical Text Information Retrievalmentioning

confidence: 99%

Effective Natural Language Processing and Interpretable Machine Learning for Structuring CT Liver-Tumor Reports

Chuang

Han

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The model does not rely on hand-crafted or external natural language processing tools, such as parts-of-speech (POS) tagger, dependency parsers, etc. Extracting semantic relation from text has been performed by a group of researchers in [15]. Two models named Rel-TNG and Type-TNG were proposed that used topic n-Grams (TNG).…”

Section: Entity-relation Extractionmentioning

confidence: 99%

Development of Knowledge Base Using Human Experience Semantic Network for Instructive Texts

2021

View full text Add to dashboard Cite

An organized knowledge structure or knowledge base plays a vital role in retaining knowledge where data are processed and organized so that machines can understand. Instructive text (iText) consists of a set of instructions to accomplish a task or operation. Hence, iText includes a group of texts having a title or name of the task or operation and step-by-step instructions on how to accomplish the task. In the case of iText, storing only entities and their relationships with other entities does not always provide a solution for capturing knowledge from iTexts as it consists of parameters and attributes of different entities and their action based on different operations or procedures and the values differ for every individual operation or procedure for the same entity. There is a research gap in iTexts that created limitations to learn about different operations, capture human experience and dynamically update knowledge for every individual operation or instruction. This research presents a knowledge base for capturing and retaining knowledge from iTexts existing in operational documents. From each iTexts, small pieces of knowledge are extracted and represented as nodes linked to one another in the form of a knowledge network called the human experience semantic network (HESN). HESN is the crucial component of our proposed knowledge base. The knowledge base also consists of domain knowledge having different classified terms and key phrases of the specific domain.

show abstract

“…For instance, it was found that some key phrases may not be present in the abstract. Multi-word phrases within the text to extend the standard bag-of-words (BoW) approach are identified in [21] by generative probabilistic models. The multi-word phrases are then used to construct knowledge graphs representing the document.…”

Section: Text Mining Of Biomedical Documentsmentioning

confidence: 99%

pdfPapers: shell-script utilities for frequency-based multi-word phrase extraction from PDF documents

Loskot¹

2021

Preprint

View full text Add to dashboard Cite

Biomedical research is intensive in processing information in the previously published papers. This motivated a lot of efforts to provide tools for text mining and information extraction from PDF documents over the past decade. The *nix (Unix/Linux) operating systems offer many tools for working with text files, however, very few such tools are available for processing the contents of PDF files. This paper reports our effort to develop shell script utilities for *nix systems with the core functionality focused on viewing and searching multiple PDF documents combining logical and regular expressions, and enabling more reliable text extraction from PDF documents with subsequent manipulation of the resulting blocks of text. Furthermore, a procedure for extracting the most frequently occurring multi-word phrases was devised and then demonstrated on several scientific papers in life sciences. Our experiments revealed that the procedure is surprisingly robust to deficiencies in text extraction and the actual scoring function used to rank the phrases in terms of their importance or relevance. The keyword relevance is strongly context dependent, the word stemming did not provide any recognizable advantage, and the stop-words should only be removed from the beginning and the end of phrases. In addition, the developed utilities were used to convert the list of acronyms and the index from a PDF e-book into a large list of biochemical terms which can be exploited in other text mining tasks. All shell scripts and data files are available in a public repository named pdfP apers on the Github. The key lesson learned in this work is that semi-automated methods combining the power of algorithms with the capabilities of research experience are the most promising for improving the research efficiency.

show abstract

Semantic relation extraction aware of N-gram features from unstructured biomedical text

Cited by 16 publications

References 19 publications

Effective Natural Language Processing and Interpretable Machine Learning for Structuring CT Liver-Tumor Reports

Effective Natural Language Processing and Interpretable Machine Learning for Structuring CT Liver-Tumor Reports

Development of Knowledge Base Using Human Experience Semantic Network for Instructive Texts

pdfPapers: shell-script utilities for frequency-based multi-word phrase extraction from PDF documents

Contact Info

Product

Resources

About