Using a multimedia semantic graph for web document visualization and summarization

Abstract

The synthesis process of document content and its visualization play a basic role in the context of knowledge representation and retrieval. Existing methods for tag-clouds generations are mostly based on text content of documents, others also consider statistical or semantic information to enrich the document summary, while precious information deriving from multimedia content is often neglected. In this paper we present a document summarization and visualization technique based on both statistical and semantic analysis of textual and visual contents. The result of our framework is a Visual Semantic Tag Cloud based on the highlighting of relevant terms in a document using some features (font size, color, etc.) showing the importance of a term compared to other ones. The semantic information is derived from a knowledge base where concepts are represented through several multimedia items. The Visual Semantic Tag Cloud can be used not only to synthesize a document but also to represent a set of documents grouped by categories using a topic detection technique based on textual and visual analysis of multimedia features. Our work aims at demonstrating that with the help of semantic analysis and the combination of textual and visual features it is possible to improve the user knowledge acquisition by means of a synthesized visualization. The whole strategy has been evaluated by means of a ground truth and compared with similar approaches. Experimental results show the effectiveness of our approach, which outperforms state-of-art algorithms in topic detection combining both visual and semantic information.

A novel semantic representation approach for web documents using deep entity linking and multidocument support

“…• The input corpus is preprocessed same as Rinaldi and Russo. 2 • Noun enrichment is done assists in identifying entity labels, performing semantic annotation and evaluating the inverse document frequency (IDF) values. • These values are given to a triple resource description framework (RDF) schema in order to get the final schema.…”

“…The semantic representation of any document makes the belonging terms unambiguous and more meaningful to search relevant answers with a semantic query. The work in Rinaldi and Russo 2 uses a clustering approach and extracts visual and textual features to represent semantic documents. Deep neural networks are combined with extensive training datasets in order to generate knowledge graphs.…”

“…The system crawls a set of web documents in order to perform feature selection, where the most relevant words are extracted from the input document. This feature selection module is similar to the preprocessing module in Rinaldi and Russo, 2 followed by a novel data summarizer. The data summarizer further enhances the advantages of the preprocessing unit by reducing the number of irrelevant lines from the input document.…”

“…In this work, a web‐crawler based approach is used to mine semantic focused data with the help of a knowledge representation schema. In order to generate such a schema, the following steps are used: The input corpus is preprocessed same as Rinaldi and Russo 2 Noun enrichment is done assists in identifying entity labels, performing semantic annotation and evaluating the inverse document frequency (IDF) values. These values are given to a triple resource description framework (RDF) schema in order to get the final schema. …”

Understanding Horizon 2020 Data: A Knowledge Graph-Based Approach

“…The work described in [22] proposes a document summarization and visualization framework based on both statistical and semantic analysis of textual and visual contents, aiming to highlight relevant terms in a document using some features (such as font size, color, etc.) showing the importance of a term compared to other ones.…”