Enhancing biomedical concept extraction using semantic relationship weights

The Semantic Web uses formal ontologies as a key instrument in order to add structure to the data, but building domain specific ontologies is still a difficult, time consuming and error-prone process since most information is currently available as free-text. Therefore the development of fast and cheap solutions for ontology learning from text is a key factor for the success and large scale adoption of the Semantic Web. Ontology development is primarily concerned with the definition of concepts and relations between them, so one of the fundamental research problems related to ontology learning is the extraction of concepts from text. To investigate this research problem we focus on the expert finding problem, i.e, the extraction of expertise topics and their assignment to individuals. The ontological concepts we extract are a person's skills, knowledge, behaviours, and capabilities. For increased efficiency, competitiveness and innovation, every company has to facilitate the identification of experts among its workforce. Even though this can be achieved by using the information gathered during the employment process and through self-assessment, a person's competencies are likely to change over time. Information about people's expertise is contained in documents available inside an organisation such as technical reports but also in publicly available resources, e.g., research articles, wiki pages, blogs, other user-generated content. The human effort required for competency management can be reduced by automatically identifying the experts and expertise topics from text. Our goal is to explore how existing technologies for concept extraction can be advanced and specialised for extracting expertise topics from text in order to build expertise profiles.

The social networking website Facebook offers to its users a feature called “status updates” (or just “status”), which allows users to create Microposts directed to all their contacts, or a subset thereof. Readers can respond to Microposts, or in addition to that also click a “Like” button to show their appreciation for a certain Micropost. Adding semantic meaning in the sense of unambiguous intended ideas to such Microposts. We can make a start towards semantic web by adding semantic annotation to web resources. Ontology are used to specify meaning of annotations. Ontology provide a vocabulary for representing and communicating knowledge about some topic and a set of semantic relationships that hold among the terms in that vocabulary. For increasing the efficiency of ontology based application there is a need to develop a mechanism that reduces the manual work in developing ontology. In this paper, we proposed Microposts’ ontology construction. In this paper we present a method that extracts meaningful knowledge from microposts shared in social platforms. This process involves different steps for the analysis of such microposts (extraction of keywords, named entities and their matching to ontological concepts).

Point cloud is an important and commonly used signal representation for volume objects or scenes in the real world. Due to the imperfect acquisition of the point cloud, there is nonnegligible noise in the point cloud. Most literatures that use graph signal processing (GSP) for point cloud denoising (PCD) generally construct k-NN graph to represent the point cloud. However, the graph constructed based on this scheme can not compactly represent the underlying structure of a noisy point cloud. In this paper, we propose a feature graph that can effectively and naturally represent the structure of the point cloud. To construct the feature graph, a feature sampling method is exploited to obtain the feature points. Then, patches are built based on the feature points. After that, the feature graph is constructed by connecting all the points in the patches. Finally, we apply the feature graph to the PCD problem and exploit graph Laplacian regularization (GLR) as smoothing prior information for denoising. Experimental results show that our proposed PCD method not only outperforms the existing PCD methods in objective evaluation metrics, but also performs better in processing the inner and edge structure of the point cloud.

The paper proposes an approach to extracting ontology concepts from the results of automatic processing the software requirements written in natural Russian-language. Relevance of developing an approach to automating the process of extraction of the ontology concepts from the requirements written in natural language is due to the necessity to maintain the requirements specification in a consistent state under conditions of business environment variability. First we discuss the advantages of the ontology-based approach to the requirements engineering as a stage of the software engineering process. The main attention is focused on the possibilities of presenting knowledge about the software application domain and requirements specification in the form of ontologies. We analyzed possibilities of automatic Russian text processing tools for extracting ontology concepts and consider such tools as ETAP-4, MaltParser and UDPipe. The choice of UDPipe as a tool for automatic processing the requirements texts is explained by the best results that it showed when analyzing texts such as software requirements. Then we describe the main classes, object properties and data properties of the proposed requirements ontology and the application domain ontology. An additional advantage of the proposed approach, increasing its practical utility, is building the system of production rules by which the analysis of the results of the automatic processing of the requirements texts obtained using the UDPipe tool.KeywordsRequirements engineeringOntologyAutomatic text processing

Classifying Multi-Label nodes in networks is a well-known and widely used task in different domains. Current classification models rely on mining the network structure either by random walks or through approximating the laplacian of the network graph which gives insight about the nodes’ neighborhood. In implicit feedback relations, these models assume all relation edges to be equally strong and important. However, in real life, this is not necessarily the case as some edges might have different semantic weights such as friendship relation. To tackle this limitation we propose in this paper a weighted two-stage multi-relational matrix factorization model with Bayesian personalized ranking loss for network classification that utilizes different weighting functions for approximating the implicit feedback relation weights. Experiments on four real-world datasets show that the proposed model significantly outperforms the state-of-art models. Results also show that selecting the right weighting functions for approximating relation weights significantly improves classification accuracy.

Objectives: To identify ontology concepts from text documents for the construction of work process ontology. Methods: This study proposes a methodology to identify terms representing a work process ontology concept from a document. The methodology encompasses several key steps: document collecting, text pre-processing, term weighting and analysis, terms mapping, and domain expert relevance judgments. A comparison between the results of three different term weighting schemes, namely the Term Frequency (TF), Term Frequency-Inverse Document Frequency (TFIDF), and Mutual Information (MI) is made with the ontology concept that the domain expert has judged. Findings: The approaches adopted in this study have managed to extract ontological concepts from the targeted domain knowledge source. The findings of the comparison analysis suggest that the TFIDF term weighting scheme exhibits better results compared to the TF and MI weighting schemes. Novelty: A work process ontology is a structured knowledge describing daily operations in the government sector. However, there has been little to no effort in building the work process ontology. This study presents an integrated approach for identifying ontology concepts from documents within the domain of the work process. To the utmost extent of our understanding, this research initiative is the initial attempt to introduce a structured methodology for the semi-automatic extraction and evaluation of concepts and relationships within this domain. The findings can be utilised as a foundation for developing an ontology in the specific field. Keywords: Ontology, Work process, Text extraction, Natural language processing, Term weighting

It is well known that the main objective of conceptual retrieval models is to go beyond simple term matching by relaxing term independence assumption through concept recognition. In this paper, we present an approach of semantic indexing and retrieval of biomedical documents through the process of identifying domain concepts extracted from the Medical Subject Headings (MeSH) thesaurus. Our indexing approach relies on a purely statistical vector space model, which represents medical documents and MeSH concepts as term vectors. By leveraging a combination of the bag-of-words concept representation and word positions in the textual features, we demonstrate that our mapping method is able to extract valuable concepts from documents. The output of this semantic mapping serves as the input to our relevance document scoring in response to a query. Experiments on the OHSUMED collection show that our semantic indexing method significantly outperforms state-of-art baselines that employ word or term statistics.

Multi-criteria linear optimization classifier with semantically weighted kernels for Chinese word formation pattern prediction

This article presents a system that carries out highly effective searches over collections of textual information, such as those found on the Internet. The system is made up of two major parts. The first part consists of an agent, Musag, that learns to relate concepts that are semantically ''similar'' to one another. In other words, this agent dynamically builds a dictionary of expressions for a given concept that captures the words people have in mind when mentioning the specific concept. We aim at achieving this by learning from the context in which these words appear. The second part consists of another agent, Sag, which is responsible for retrieving documents, given a set of keywords with relative weights. This retrieval makes use of the dictionary learned by Musag, in the sense that the documents to be retrieved for a query are related to the concept given according to the context of previously scanned documents. In this way, we overcome two main problems with current text search engines, which are largely based on syntactic methods. One problem is that the keyword given in the query might have ambiguous meaning, leading to the retrieval of documents not related to the topic requested. The second problem concerns relevant documents that will not be recommended to the user, since they did not include the specific keyword mentioned in the query. Using context learning methods, we will be able to retrieve such documents if they include other words, learned by Musag, that are related to the main concept. We describe the agents'system architecture, along with the nature of their interactions. We describe our learning and search algorithms and present results from experiments performed on specific concepts. We also discuss the notion of ''cost of learning'' and how it influences the learning process and the quality of the dictionary at any given time.

Biomedical information is available to research and development scientists as unstructured text in the form of scientific manuscripts and reports published in the literature and elsewhere. Scientists focused on specific research programs are burdened with surveying vast numbers of publications and reports to acquire information relevant to their efforts. Employing technology as a research aid provides a mechanism to cope with information overload that characterizes the R&D environment. Text mining can extract knowledge from large corpora of biomedical text and make it available to support scientific research and knowledge collections [1, 2] and intelligent PDF reader tools able to search content and find related articles [3] are available; however, such reader tools are typically desktop applications limited to specific platforms and data sources so they cannot easily support broad based integrated scientific search needs for a dispersed R&D organization with a wide variety of content needs. Our team has developed a web-browser based document reader with a built-in exploration tool and automatic concept extraction from biomedical text content. This provides R&D scientists with a simple tool to aid finding, reading, and exploring documents relevant to focused research objectives. The tool, Shangri-Docs, combines a document reader with automatic concept extraction and highlighting of relevant terms based on carefully selected ontologies combined with our custom corporate enterprise taxonomy. Shangri-Docs provides the ability to evaluate a wide variety of document formats (e.g. PDF, Word, PPT, text, etc.) and exploits the linked nature of the Web and personal content by performing searches on content from public sites (e.g. Wikipedia, PubMed) and privately cataloged databases simultaneously. Shangri-Docs incorporates Apache cTAKES (clinical Text Analysis and Knowledge Extraction System) [4] and Unified Medical Language System (UMLS) to automatically identify and highlight terms and concepts, such as specific pathology, disease, drug, and biological terms mentioned in the text. cTAKES was originally designed specifically to extract information from clinical medical records. We have extended cTAKES automatic knowledge extraction process to include the R&D biomedical research domain by improving the ontology guided information extraction process. Shangri-Docs could be adapted to other science fields and further customized across our R&D scientific community via our open source, cloud-based, data management system. [1] Funk, et.al., BMC Bioinformatics 2014, 15:59 doi:10.1186/1471-2105-15-59 [2] Kang et al., BMC Bioinformatics 2014, 15:64 doi:10.1186/1471-2105-15-64 [3] Utopia Documents, http://utopiadocs.com [4] Apache cTAKES, http://ctakes.apache.org Citation Format: Chris Mattmann, Lauren Intagliata, Selina Chu, Garth McGrath, Giuseppe Totaro, Daniel Civello, David Ballard, Jeffrey Long, Nipurn Doshi, Shivika Thapar, Michael Livstone, Paul Ramirez, Maureen Cronin. Shangri-Docs: a browser based tool for document exploration and automatic knowledge extraction from unstructured biomedical text. [abstract]. In: Proceedings of the 107th Annual Meeting of the American Association for Cancer Research; 2016 Apr 16-20; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2016;76(14 Suppl):Abstract nr 5283.

In this paper, based on the dynamic space of drought climate change detection in mountainous areas, an in-depth study on the green economic efficiency of high-tech industry is carried out. Under the background of climate change in mountainous areas, this paper puts forward some reference suggestions by concentrating the structural sequence of “layer structure” in the form of mountain climate landscape and incorporating it into a unified dialectic design concept. The process derived from layer construction not only is the process of continuous concept extraction and construction in dynamic space design, but also represents a new strategic method and direction guide for exploring dynamic space theory, and represents an important point for the rational development of current and future dynamic space. The modernization of high-tech industry is not only the driving force of material and economic development, but also the solid foundation of sustainable development of real economy. Among them, the financial market is an important way of real economy action. Close monitoring of financial markets and modernization of their industrial structure can reduce the financing opportunities that deviate from IMF. The existence of financial market in the process of industrial structure modernization is conducive to the formation of a sound industrial structure, and the effective cooperation between financial market and high-tech industrial structure modernization will promote the real economic development. Therefore, it is of great significance to systematically study the impact of financial development, industrial structure upgrading, and the integration of the two on the real economy. In this paper, the drought climate change in mountainous areas and the green economic efficiency of high-tech industry are studied, and applied to the dynamic space, aiming to promote the application in practice.

Finding relevant information is a big challenge in today's information retrieval domain. Various applications need to find objects closest to the mentioned location that has a set of keywords. In a spatial dataset, objects are linked with some keyword(s) which specify their features. Closest Keywords is a method to query objects, using keyword cover. Algorithm based on Closest Keywords Search which exhaustively combines objects from different query keywords for generating candidate keyword covers. The increasing importance of keyword rating in object evaluation helps for the better decision making. This triggers to generate Best Keyword Cover which mainly considers inter-objects distance as well as the keyword rating of objects. When the number of query keywords gets increases, the performance of the closest keyword cover search algorithm drops significantly as a result of huge candidate keyword covers generated. To overcome this drawback, much more scalable algorithm known as keyword nearest neighbor expansion (keyword-NNE) has been proposed. Keyword-NNE algorithm significantly reduces number of candidate keyword covers generated.

To address the issues of modeling the relationships between multiple local region objects in images and enhancing local region features, as well as mapping global image semantics to global text semantics and local region image semantics to local text semantics, a novel image captioning method based on CLIP and integrating local feature enhancement and multi-scale semantic guidance is proposed. The model employs ViT as the global visual encoder, Faster R-CNN as the local region visual encoder, BERT as the text encoder, and GPT-2 as the text decoder. By constructing a KNN graph of local image features, the model models the relationships between local region objects and then enhances the local region features using a graph attention network. Additionally, a multi-scale semantic guidance method is utilized to calculate the global and local semantic weights, thereby improving the accuracy of scene description and attribute detail description generated by the GPT-2 decoder. Evaluated on MSCOCO and Flickr30k datasets, the model achieves a significant improvement in the core metric CIDEr over established strong baselines, with 4.7% higher CIDEr than OFA on MSCOCO, and 16.6% higher CIDEr than Unified VLP on Flickr30k. Ablation studies and qualitative analysis validate the effectiveness of each proposed module.

Keyword extraction is the task of identifying important terms or phrase that are most representative of the sourcedocument. Although the process of automatic extraction of keywords from title is an old method, it was mainly forextraction from a single web document. Our approach differs from previous research works on keyword extraction in severalaspects. For those who are non-expert of the scientific fields, understating scientific research trends is difficult. The purposeof this study is to develop an automatic method of obtaining overviews of a scientific field for non-experts by capturingresearch trends. This empirical study excavates significant term extraction using Natural Language Processing (NLP) tools.More than 15000 titles saved in a .csv file was our dataset and scripts written in Python were our process to compare how farsignificant terms of scientific title corpus are similar or different to the terms available in the abstract of that same scientificarticle corpus. A light-weight unsupervised title extractor, Yet Another Keyword Extractor (YAKE) was used to extract theresults. Based on our analysis, it can be concluded that these algorithms can be used for other fields too by the non-expertsof that subject field to perform automatic extraction of significant words and understanding trends. Our algorithm could be asolution to reduce the labour-intensive manual indexing process.

During the last two decades, natural language processing (NLP) puts a tremendous impact on automated text generation. There are various important libraries in NLP that aid in the development of advanced applications in a variety of sectors, most notably education, with a focus on learning and assessment. In the learning environment, objective evaluation is a common approach to assessing student performance. Multiple-choice questions (MCQs) are a popular form of evaluation and self-assessment in both traditional and electronic learning contexts. A system that generates multiple-choice questions automatically would be extremely beneficial to teachers. The objective of this study is to develop an NLP based system, Quru (Question Guru), to produce questions automatically from text content. The Quru is broken into three basic steps to construct an automated MCQs generation system: Stem Extraction (Important Sentences Selection), Keyword Extraction, and Distractor Generation. Furthermore, the system's performance is validated by university lecturers. As per the findings, the MCQs generated are more than 80% accurate.KeywordsKeyword extractionMCQsNLPQuestion generationAutomated questions