Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Knowledge extraction”

Knowledge extraction

Brighenti, Chiara, Brighenti, Attilio, Biancat, Jacopo et al. · Comillas Repository (Comillas Pontifical University) · 2016

Cited by 0

Thematic knowledge extraction

Zhang, Shaomin · Nottingham Trent University's Institutional Repository (Nottingham Trent Repository) · 2003

This thesis describes research into automatic knowledge extraction (AKE) from text. In particular, the automatic knowledge extraction is to produce or help to produce knowledge in the format of an existing hypermedia knowledge-based system: HyperTutor. The whole AKE process is divided into two main stages: concept extraction and relation extraction. 
\n 
\nAutomatic thematic concept (keyword) extraction (TCE) is described in detail. Two approaches for TCE are presented and evaluated. One of them is a machine learning approach based on artificial neural networks (ANNs). New measures of evaluation of this novel approach are introduced, based on the concept of generalisation. These include natural generalisation (NG) and pure generalisation (PG). Measures commonly used in knowledge extraction research, i.e. recall and precision, are applied in their normal binary form, but analogue versions are developed to assess the performance of the ANN-based approach. A comparison with chance (GWC) measure is also applied to the results. A stemming analysis method has also been attempted at sense-level and word-level. The results show that thematic concepts can be automatically extracted from text using an ANN plus a lexical semantic resource. The ANN alone produces best result for non-keywords and overall. Word level stemming analysis alone is the best for identifying keywords, while sense level analysis provides the most balanced results between keywords and non-keywords. The baseline comparison for the ANN method shows that the ANN method adds value to the external lexicon. The CWC measure shows that both the ANN and stemming methods work much better than chance.
\n 
\nDomain portability of the keyword extraction techniques developed is addressed. Although the ANN itself in not transferable, the ANN method is transferable with consistent performance between domains. The stemming analysis approach also transfers well between domains, although not as well as the ANN method. 
\n 
\nAn attempt to answer the question of how the ANN learns the problem of thematic concept extraction is also presented, based on the analysis of the weights in the trained ANN. Analysis is carried out on three different aspects: relation level analysis tries to find out if some kind of relations are more important than others, or if they are equally important to the ANN; path level analysis aims to identify what kinds of paths are more likely to lead to a noun being classified as a keyword; and analysis of category information helps to explain how category affects keyword recognition. This analysis has confirmed the hypothesis of close relationships that are distinct and characteristic of the seed word-KW relationship. 
\n 
\nAn important type of relation, named verb-noun relation, is targeted in the attempt of relation extraction. This is novel. Parse tree based and tagger based approaches have been investigated. The parse tree based method produces high precision and low recall. The main reason for the low recall is parser failure. This reflects the current limitation of the parser techniques is not advanced enough to process texts in the real world. The tagger-based approach produces high recall and low precision. The style of writing may have great impact on the results of relation extraction. The experiments have shown that both of the approaches perform better for one of the documents compared with the other. 
\n 
\nThis thesis also proposes issues for future work in AKE research.

Cited by 0Open access

Knowledge Extraction Using . . .

Aldo Dragoni, Luigi Lella, et al. · 1999

We present a system that extracts knowledge from the textual content of documents. The acquired knowledge is represented through an associative network, that is dynamically updated by the integration of a contextualized structure representing the content of the new analysed document. Grounded on the basis of “long term working memory” theory by W. Kintsch and K.A. Ericsson, our system makes use of a scale free graph model to update the final knowledge representation. This knowledge acquisition system has been validated by first experimental results.

Cited by 0

Pubmed Knowledge Base (Extraction)

Colia, Gabriele · AMS Degree Thesis (University of Bologna) · 2020

Questo elaborato propone la creazione di un indice di articoli medici raggruppati all'interno di Pubmed. Pubmed è un motore di ricerca scientifico noto all'interno della comunità medica, in cui gli esperti del settore condividono articoli clinici affini ad ogni ambito della medicina.
\nPer via della sua estensione e notorietà si ritiene che Pubmed contenga tutto il know how medico necessario a poter realizzare un corpus di documenti su cui poter effettuare future analisi intelligenti automatiche.

Cited by 0

Knowledge extraction from images

Muhammad Shafiq Shith · DR-NTU (Nanyang Technological University) · 2015

Knowledge extraction from images is obtaining valuable information for various purposes. Extraction of text, titles, descriptions and etc. As online image search engines progressed and developed over time, it has change how we use these tools for online searches. We constantly find ways to improve and innovate the current concepts of image searching. However, there are always limitations to what a computer can accomplish. Based on application such as Machine Learning and Image Processing, a search can be better refined if we could enhance the search engines to think like a human. This project aims to find a way to extract valuable information from images searches and provide a use for those information.

Cited by 0

Knowledge Enabled Relation Extraction

Monika Jain · 2024

Relation extraction is the task of extracting relationships from input text, where input can be a sentence, document, or multiple documents. This task has been popular for decades and is still of keen interest. Various techniques have been proposed to solve the relation extraction problem, among which the most popular are using distant supervision, deep learning-based models, reasoning-based models, and transformer-based models. We propose three approaches (named ReOnto, DocRE-CLip, and KDocRE) for relation extraction from text at three levels of granularity (sentence, document and across documents). These approaches embed knowledge in a deep learning based model to improve performance. ReOnto and DocRE-CLip have been evaluated and the source code is publicly available. We are currently implementing and evaluating KDocRE.

Cited by 0Open access

Knowledge Extraction from Data

Vladislav Kozák · Digital Repository (National Repository of Grey Literature) · 2009

The task of this master thesis is to describe the overall process of data mining and algorithms used for data preparation and data modelling. The qualities of these algorithms are compared and the results are well-founded with repeatable tests. Knowledge gained by this research is applied to 2 real data based tasks. Master thesis includes development of own data mining application. The stress was laid on robustness, intuitive GUI as well as wide spectrum of data mining algorithms implemented.

Cited by 0

Neural Network Knowledge Extraction

Alexandra I. Cristea, Paul D. Cristea, Toshio Okamoto et al. · 1997

The usage of ANNs in "safety-critical" domains, which include the economic and financial applications, is hindered by their "black box"- type approach, which makes it difficult to verify and debug software that includes ANN components. Significant advantages can be gained by combining the symbolic knowledge of a domain theory (DT), with the empirical sub-symbolic knowledge stored in an ANN trained on examples. Rule extraction adds the needed explanation/comprehension component to the much prized ability of ANN to generalise over a learned set of examples. Compiling rules into the an ANN provides better initial conditions for training the network and can significantly improve the speed of learning. The mixed approach allows building hybrid systems that co-operatively combine ANN and AI techniques, increasing both robustness and flexibility. The paper gives an overview of the bases of ANN knowledge extraction under the form of logical functions. ANN design relations are established. 1.

Cited by 0

Towards Unsupervised Knowledge Extraction

Dorothea Tsatsou, Konstantinos Karageorgos, Anastasios Dimou et al. · e-Archivo (Carlos III University of Madrid) · 2021

Integration of symbolic and sub-symbolic approaches is rapidly emerging as an Artificial Intelligence (AI) paradigm. This paper presents a proof-of-concept approach towards an unsupervised learning method, based on Restricted Boltzmann Machines (RBMs), for extracting semantic associations among prominent entities within data. Validation of the approach is performed in two datasets that connect language and vision, namely Visual Genome and GQA. A methodology to formally structure the extracted knowledge for subsequent use through reasoning engines is also offered.

Cited by 1Open access

D3.1 Knowledge extraction models

EURECAT · Zenodo (CERN European Organization for Nuclear Research) · 2022

In this document, we present the metrics, methods, and results of the analysis of data from existing prosumer communities performed in T3.1, that set the bases for the development of the Prosumer Intelligence Toolkit. Research questions were defined after conversation with project partners and stakeholders, and interviews and focus groups with publishers, organized in the framework of WP2. For addressing these research questions, we collected and analyzed digital traces of user interactions among thousands of users from three popular prosumer platforms in which users co-create content: a fanfiction community where users create works based on existing fictional universes, and review one another’s work (AO3); a fandom wiki, where users create content collaborating on editing wiki pages to document any element related to a fictional universe (Fandom); and a social reading platform, where users create original stories and read and comment on one another’s work (Wattpad). The central part of the document includes: An analysis of popularity dynamics in AO3, and a model to predict works that will become very popular in the near future, based on previous history. We have further re- adapted the model to apply it on tags, and predict topics that will become popular. Both with work and tag popularity prediction, we obtained a satisfactory accuracy with a simple and interpretable model. This responds to an emerging need of publishers and stakeholders to identify trending content and topics, and may help to understand trends in the interests of readers and writers, and to identify valuable content to be considered for publishing. An analysis of social interactions between AO3 users, modelled as graphs, studying structural properties of the social networks resulting from different kinds of interactions, and the centrality of the users in the community. We characterized each user by the combination of their centrality as a producer (feedback received an author) and as an active consumer (feedback given as a reader) in the network, finding consistent clusters across the major communities, that suggest the existence of different emerging profiles, among which the ones we dubbed superproducers, superconsumers, and superprosumers, as the users who have the highest levels of centrality in one of the two dimensions, or in both. We believe this “map” of prosumer roles may be helpful to understand the composition of a community and identify relevant users for specific aims. An analysis of collective dynamics in Fandom wikis, studying how activity on different tasks and spaces evolves over time and in different phases of community growth, for different communities, with an investigation on peaks of activity and their nature in the life of a community. The most edited pages result to be related to the main characters of each fictional universe. The amount of activity devoted to parallel spaces beyond D3.1 Knowledge extraction models Page 3 of 106 editing the main content of the wiki (e.g. coordination, communication, technical aspects) varies substantially across communities; as a general tendency, the proportion of the effort spent for personal communication and interactions increases during the periods of higher activity in a community. • An analysis of the dynamics, and the language and emotion of users’ feedback on a sample of very popular books from two diverse Wattpad categories: teen literature and classics. We found a tendency to have more activity on the first and last chapters of a book, and we have shown how language in the feedback around each book, and across books, can be characterized and compared through different tools for language and emotional analysis. Finally, the document presents lines for future research and some preliminary ideas for the development of interactive dashboards in the Prosumer Intelligence Toolkit, to be developed in task T3.2.

Cited by 0Open access

Knowledge Information Extraction Research

2025

This Reprint presents recent advances in the rapidly evolving field of Knowledge and Information Extraction Research, with a particular emphasis on methods that transform heterogeneous and unstructured data into structured, actionable knowledge. It brings together diverse contributions exploring methodological innovations across natural language processing, machine learning, data mining, information retrieval, and knowledge graph construction. By integrating these perspectives, the Reprint demonstrates how technical progress in algorithm design and system development is reshaping the landscape of intelligent information management.The Reprint highlights the growing importance of precision, scalability, and interpretability in modern extraction techniques. Selected articles address challenges such as extracting semantics from complex texts, modeling relationships within large-scale knowledge graphs, and applying deep learning approaches to enhance efficiency and reliability. Interdisciplinary collaboration emerges as a recurring theme, underscoring how computational methods can be successfully combined with domain-specific expertise to tackle real-world problems. Contributions illustrate how advanced knowledge extraction techniques can drive innovation in healthcare, finance, e-commerce, cybersecurity, and other data-intensive sectors. By bridging theoretical development with implementation in practice, the Reprint demonstrates its role not only as a record of scholarly progress but also as a resource for practitioners seeking solutions to pressing information challenges.

Cited by 0Open access

Example of knowledge extraction.

Yan Liang (139654), Bingxue Xie (10661505), Wei Tan (123562) et al. · Figshare · 2025

<div> The fine-grained mining and construction of semantic associations within multimodal intangible cultural heritage (ICH) resources are crucial for deepening our understanding of their knowledge content and ensuring their systematic protection and transmission in the digital and intelligent era. This paper addresses the urgent need for the digital preservation and transmission of ICH resources. Following a review of current research on Qingyang sachets and ICH, the study introduces an ontology-based approach to constructing a semantic description model for the multimodal digital resources related to Qingyang sachets. By acquiring and processing multimodal resources concerning the craftsmanship and associated customs of Qingyang sachets, the study reorganizes the corresponding textual and visual knowledge. Utilizing knowledge graphs, the research explores multidimensional pathways for delivering knowledge services related to the multimodal digital resources of Qingyang sachets. Empirical research confirms the applicability and feasibility of the proposed semantic association scheme for multimodal ICH digital resources. The findings provide valuable insights for multidimensional organization and integration across scenarios, time periods, and resources within the ICH domain, offering a reference for digital solutions aimed at the systematic protection of ICH. </div>

Cited by 0Open access

Knowledge Discovery and Extraction

Leslie D. Cumiford · 2006

Report Documentation Page Form ApprovedOMB No. 0704-0188 Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number.

Cited by 0

Webnox: web knowledge extraction

David Urbansky, James A. Thom, Marius Feldmann · RMIT Research Repository (RMIT University Library) · 2008

The paper describes and evaluates a system for extracting knowledge from the web that uses a domain independent fact extraction approach and a self supervised learning algorithm. Using a trust algorithm, the precision of the system is improved to over 70% compared with a baseline of 52%. The paper describes and evaluates a system for extracting knowledge from the web that uses a domain independent fact extraction approach and a self supervised learning algorithm. Using a trust algorithm, the precision of the system is improved to over 70% compared with a baseline of 52%. The paper describes and evaluates a system for extracting knowledge from the web that uses a domain independent fact extraction approach and a self supervised learning algorithm. Using a trust algorithm, the precision of the system is improved to over 70% compared with a baseline of 52%. The paper describes and evaluates a system for extracting knowledge from the web that uses a domain independent fact extraction approach and a self supervised learning algorithm. Using a trust algorithm, the precision of the system is improved to over 70% compared with a baseline of 52%. The paper describes and evaluates a system for extracting knowledge from the web that uses a domain independent fact extraction approach and a self supervised learning algorithm. Using a trust algorithm, the precision of the system is improved to over 70% compared with a baseline of 52%.

Cited by 4

Open Knowledge Extraction Challenge

Andrea Giovanni Nuzzolese, Anna Lisa Gentile, Valentina Presutti et al. · Communications in computer and information science · 2015

Cited by 45