The Advancements and Progresses of Artificial Intelligence-Based Keyword Extraction Methods

DOI

10.2991/978-94-6463-512-6_61How to use a DOI?

Keywords

Artificial Intelligence; Machine Learning; Deep Learning; Keyword Extraction

Abstract

Keywords can provide general and significant information about documents; they allow readers to overview the text before deciding whether to read through or not. However manually selecting keywords from texts faces problems such as time consumption so efficient automatic keyword extraction methods are required. In this paper the author discussed four different Artificial Intelligence (AI) models that were designed to complete the task of keyword extraction. Two of the models introduced used machine learning methods and deep learning was adopted in the other two. The machine learning methods include decision tree and the Kea algorithm both of them were supervised trained. The former uses the C4.5 algorithm to generate decision trees and the latter uses the Naïve Bayes model to put words into classes. Deep learning models used Artificial Neural Networks (ANN) and the Long Short-Term Memory (LSTM). The ANN model consists of weighted layers that take four features of a word as inputs and returns one value that determines the class of the word. The LSTM model uses two networks and the results from the networks are combined and passed into an attention layer to produce a vector that is to be used to classify the words. The models have problems with interpretability and distribution of data which further works can be done on expert systems and domain adaptation to enhance the models from these problems. The paper summarizes the progress and potential improvements to the field of AI-based keyword extraction and can be used as reference for studying

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Hexuan Deng
PY  - 2024
DA  - 2024/09/23
TI  - The Advancements and Progresses of Artificial Intelligence-Based Keyword Extraction Methods
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 580
EP  - 585
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_61
DO  - 10.2991/978-94-6463-512-6_61
ID  - Deng2024
ER  -