Detection of Context-Dependent Lexical Information from Unstructured Data Using Word Embeddings Based on Machine Learning: An Assessment

Amit Shukla, Rajendra Gupta

2023

Abstract

In the current generation of context-dependent information solutions, data discovery and identification engines rely on rule-based models in most cases, and they are confined to context-independent lexical data in unstructured data such as formless text or images. Data elements that are always considered lexical, regardless of the context in which they reside, are known as context-independent lexical data. The unstructured lexical data is the data that isn’t arranged according to a pre-determined data schema and can’t be saved in traditional relational database. Text and multimedia are two types of unstructured data that are regularly analyzed. The paper presents a Context - Centered Extraction of Concepts (CCEC) word embeddings method the gives benefit from a neural-network methods ability to encode textual information by converting meaningful text information into numeric values. The result shows about 90 per cent accuracy in targeting context-dependent lexical information by considering the context of the words in a sentence/text.

Paper Citation

in Harvard Style

Shukla A. and Gupta R. (2023). Detection of Context-Dependent Lexical Information from Unstructured Data Using Word Embeddings Based on Machine Learning: An Assessment. In Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT; ISBN 978-989-758-661-3, SciTePress, pages 533-536. DOI: 10.5220/0012603900003739

in Bibtex Style

@conference{ai4iot23,
author={Amit Shukla and Rajendra Gupta},
title={Detection of Context-Dependent Lexical Information from Unstructured Data Using Word Embeddings Based on Machine Learning: An Assessment},
booktitle={Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT},
year={2023},
pages={533-536},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012603900003739},
isbn={978-989-758-661-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT
TI - Detection of Context-Dependent Lexical Information from Unstructured Data Using Word Embeddings Based on Machine Learning: An Assessment
SN - 978-989-758-661-3
AU - Shukla A.
AU - Gupta R.
PY - 2023
SP - 533
EP - 536
DO - 10.5220/0012603900003739
PB - SciTePress