Knowledge Based Summarization and Document Generation using Bayesian Network

Malviya, Shrikant; Tiwary, Uma Shanker

doi:10.1016/j.procs.2016.06.080

Cited by 10 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The set G{Xi}, i N{1, …, 19} was defined. The set of edges was { n}, where n = Xi |πi = PBN (Xi |πi), demonstrating the probability of Xi conditioned on πi [58]. For each element of set G{Xi}, an alternative set x{xi,j} was assigned, j N. For nodes X1: type of material x {powder, filament}, X2: type of laser x {I, II, III, IV, V, VI, VII}, X3: material x {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12}, X4 to X18: "properties tested," where x {0 "no" or 1 "yes"}, and X19: IF x {A, B, C, D, E, F}, according to the rules defined for the representation of expert knowledge.…”

Section: Results Of Bayes Algorithms Applicationmentioning

confidence: 99%

Single Tracks as a Key Factor in Additive Manufacturing Technology—Analysis of Research Trends and Metal Deposition Behavior

et al. 2020

View full text Add to dashboard Cite

In recent years, general studies on Selective Laser Melting (SLM)/Selective Laser Sintering (SLS)/direct metal deposition (DMD) technologies, as well as studies on detailed issues in this area, have been carried out. However, a research gap is observed in investigations into the features of single tracks in the above-mentioned technologies. On the basis of data published in 2016–2019, an approach was adopted for a preliminary quantitative analysis of the knowledge base and also trends observed in the development of new technologies. This study demonstrates the effectiveness of the data mining technique based on the Bayes algorithm for analyzing trends in processes of additive manufacturing and the practical application of the knowledge received using the Bayes algorithm. After the analyses referred to above were completed, single and double layers of a composite material based on the Ni-based alloy and Fe–Al bronze were analyzed under different processing conditions. The effects of laser spot speeds and pitches on microhardness, microstructure, and interlayers’ features were described. So, the innovative approach, namely, the combination of the analysis of the scientific database of the phenomenon under study and the subsequent experimental investigation of its features, is the scientific novelty of the present study.

show abstract

Section: Results Of Bayes Algorithms Applicationmentioning

confidence: 99%

Single Tracks as a Key Factor in Additive Manufacturing Technology—Analysis of Research Trends and Metal Deposition Behavior

et al. 2020

View full text Add to dashboard Cite

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Generating a text summary from a collection of text documents retrieved based on the query given by a user [6,7] using semantic knowledge extraction techniques is another application in KG. The Summarized Research Article Generator (SRAG) introduced by Malviya et al [6] stores the semantic knowledge of each research paper, which is extracted through a query in the form of a semantic tree. A probabilistic model based on a Bayesian network is used to extract the relevant information from the semantic tree, and finally, the summarized article is generated segment-wise by merging only the most relevant paragraphs to maintain coherency.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Facts or information extraction from source text frequently end up with erroneous facts. As a solution for this, Cohen et al proposed a methodology to jointly evaluate the extracted facts [6], but the issue with this methodology was its consideration of only the trivial set of possible errors that could arise in extracted facts. Elhammadi et al [3] proposed a Conditional Random Field (CRF) model to recognize and remove sequences of noisy text frequently found in financial news articles.…”

Section: Knowledge Graph Completion (Kgc)mentioning

confidence: 99%

See 1 more Smart Citation

Knowledge Graphs Representation for Event-Related E-News Articles

Lakshika

Caldera

2021

MAKE

View full text Add to dashboard Cite

E-newspaper readers are overloaded with massive texts on e-news articles, and they usually mislead the reader who reads and understands information. Thus, there is an urgent need for a technology that can automatically represent the gist of these e-news articles more quickly. Currently, popular machine learning approaches have greatly improved presentation accuracy compared to traditional methods, but they cannot be accommodated with the contextual information to acquire higher-level abstraction. Recent research efforts in knowledge representation using graph approaches are neither user-driven nor flexible to deviations in the data. Thus, there is a striking concentration on constructing knowledge graphs by combining the background information related to the subjects in text documents. We propose an enhanced representation of a scalable knowledge graph by automatically extracting the information from the corpus of e-news articles and determine whether a knowledge graph can be used as an efficient application in analyzing and generating knowledge representation from the extracted e-news corpus. This knowledge graph consists of a knowledge base built using triples that automatically produce knowledge representation from e-news articles. Inclusively, it has been observed that the proposed knowledge graph generates a comprehensive and precise knowledge representation for the corpus of e-news articles.

show abstract

“…The proposed MDS (Multi Document Summarization) is a kind of query-based extractive summarizer. It retrieves the relevant content from the knowledge tree based on its score [35]. Better summaries can be given by using spatial information based retrieval content.…”

Section: Shrikant Malviya and Uma Shanker Tiwary (2016)mentioning

confidence: 99%

Review and Comparative Analysis of Topic Identification Techniques

Sehrawat¹

2019

IJATCSE

View full text Add to dashboard Cite

Topic identification is an area of data mining that finds common text/ themes from several documents. It is a data summarization technique that helps to summarize documents. This area is of great interest among researchers as its applications in the real world are very wide. This paper presents a review of topic identification techniques. Existing solutions include text clustering, latent semantic approach, probabilistic latent semantics approach, latent Dirichlet allocation approach, association rule-based approaches, document clustering, and soft computing approach. Soft computing techniques including fuzzy logic, neural networks, support vector machine, ant colony optimization, swarm optimization, and their hybrid approaches provide a good solution for text clustering. This paper presents a comparative study of different text mining techniques with their strengths and weaknesses. A future dimension is also proposed to develop a hybrid approach for topic identification using different techniques.

show abstract

Knowledge Based Summarization and Document Generation using Bayesian Network

Cited by 10 publications

References 10 publications

Single Tracks as a Key Factor in Additive Manufacturing Technology—Analysis of Research Trends and Metal Deposition Behavior

Single Tracks as a Key Factor in Additive Manufacturing Technology—Analysis of Research Trends and Metal Deposition Behavior

Knowledge Graphs Representation for Event-Related E-News Articles

Review and Comparative Analysis of Topic Identification Techniques

Contact Info

Product

Resources

About