A concept-driven biomedical knowledge extraction and visualization framework for conceptualization of text corpora

Abstract

A number of techniques such as information extraction, document classification, document clustering and information visualization have been developed to ease extraction and understanding of information embedded within text documents. However, knowledge that is embedded in natural language texts is difficult to extract using simple pattern matching techniques and most of these methods do not help users directly understand key concepts and their semantic relationships in document corpora, which are critical for capturing their conceptual structures. The problem arises due to the fact that most of the information is embedded within unstructured or semi-structured texts that computers can not interpret very easily. In this paper, we have presented a novel Biomedical Knowledge Extraction and Visualization framework, BioKEVis to identify key information components from biomedical text documents. The information components are centered on key concepts. BioKEVis applies linguistic analysis and Latent Semantic Analysis (LSA) to identify key concepts. The information component extraction principle is based on natural language processing techniques and semantic-based analysis. The system is also integrated with a biomedical named entity recognizer, ABNER, to tag genes, proteins and other entity names in the text. We have also presented a method for collating information extracted from multiple sources to generate semantic network. The network provides distinct user perspectives and allows navigation over documents with similar information components and is also used to provide a comprehensive view of the collection. The system stores the extracted information components in a structured repository which is integrated with a query-processing module to handle biomedical queries over text documents. We have also proposed a document ranking mechanism to present retrieved documents in order of their relevance to the user query.

A Review of Towered Big-Data Service Model for Biomedical Text-Mining Databases

“…Few of the previous studies have proposed a framework for identifying key information components from biomedical text documents, such as [55], [82] and [74], [84]. But, the precision of the extricated relations was influenced by various issues, for example, the impediment of the extraction designs and the nature of the sources.…”

“…Jahiruddin et al [74] introduced an innovative Biomedical Knowledge Extraction and Visualization framework (BioKEV) which is used to discern and isolate vital information components from biomedical text documents. The method of information extraction was based on NLP or Natural Language Processing methods and analysis that were also based on semantics.…”

A Multi-intelligent Agent Architecture for Knowledge Extraction: Novel Approaches for Automatic Production Rules Extraction

“…in that sentence. For POS analysis we have used the Stanford parser, which is a probabilistic natural language parser recognizing the grammatical structure of sentences [36,35]. In the proposed TMIA the Stanford parser receives paragraph as input and convert each sentence in that paragraph into an equivalent grammatical structure tree.…”

Effective use of latent semantic indexing and computational linguistics in biological and biomedical applications

“…LSI, in conjunction with other natural language processing techniques, can be used to interpret key concepts from a corpus and project it back to the user in graphical form. Jahiruddin et al implemented this concept by creating BioKEVis, a search interface that produces semantic nets for the visualization of biomedical knowledge from PubMed (Jahiruddin et al, 2010). Second, LSI's ability to reduce dimensionality allows for a better visualization of high-dimensionality points that exceed the realm of physical space.…”

“…For large term-document matrices, such computation is unfeasible. However, since only the reduce-rank matrix of the SVD of M is used for LSI, one can perform “rank-reduced” SVD on M, yielding a computational complexity of O ( m × n × k ), which is more scalable (Jahiruddin et al, 2010). In addition, along with high k values and inherent computational complexities, the future application of LSI to biomedical data may be hampered by the ever-increasing need for expanded data storage space.…”