Normal view MARC view ISBD view

An Enhancement of Glove algorithm for extractive text summarization of news articles. 6

By: Alter C. Orbino Jr. Seth Gabriel F. Payumo. 4 0 16, [, ] | [, ] |

Contributor(s): 5 6 [] |

Language: Unknown language code Summary language: Unknown language code Original language: Unknown language code Series: ; 46Edition: Description: Content type: text Media type: unmediated Carrier type: volumeISBN: ISSN: 2Other title: 6 []Uniform titles: | | Related works: 1 40 6 []Subject(s): -- 2 -- 0 -- -- | -- 2 -- 0 -- 6 -- | 2 0 -- | -- -- 20 -- | | -- -- -- -- 20 -- | -- -- -- 20 -- --Genre/Form: -- 2 -- Additional physical formats: DDC classification: | LOC classification: | | 2Other classification:

Contents:

Action note: In: Summary: ABSTRACT This research study addresses the limitations of the GloVe (Global Vectors for Word Representation) algorithm in the context of extractive text summarization, focusing on mitigating sparsity issues and enhancing contextual representation. The study begins by identifying three key challenges faced by GloVe: sparsity issues impacting representation accuracy, high computational demands, and difficulties in capturing contextual semantics. Firstly, the study introduces methods to mitigate sparsity issues in GloVe embeddings. By focusing on handling out-of-vocabulary words and improving the representation of rare terms, the algorithm aims to provide a more comprehensive representation of the entire corpus. Techniques such as subword embeddings and adaptive learning rates employed to address this challenge effectively. Secondly, to address the computational intensity and memory requirements of GloVe, the thesis incorporates dimensionality reduction techniques, specifically t-distributed Stochastic Neighbor Embedding (t-SNE). By reducing the dimensionality of the word embeddings, the algorithm achieves significant improvements in processing speed and memory efficiency without sacrificing summarization quality. Finally, the study enhances the contextual representation learned by GloVe for text summarization purposes. By weighing rare words and giving them better representation, the algorithm improves its ability to capture contextual semantics, thereby enhancing the quality of extractive text summarization. Through a series of experiments and evaluations using real-world news article datasets, the proposed enhancements are thoroughly validated. The results demonstrate notable improvements in the summarization performance of the enhanced GloVe algorithm compared to traditional GloVe implementations. The findings of this thesis contribute to advancing the state-of-the-art in extractive text summarization techniques and provice valuable insights for future research in natural language processing and machine learning. Other editions:

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 1 )
Title notes
Comments ( 0 )

Item type	Current location	Home library	Collection	Call number	Status	Date due	Barcode	Item holds
Book	PLM	PLM Filipiniana Section	Filipiniana-Thesis	QA76.9.N38 O73 2024 (Browse shelf)	Available		FT7848

Total holds: 0

Undergraduate Thesis : (Bachelor of Science in Computer Science) - Pamantasan ng Lungsod ng Maynila, 2024. 56

ABSTRACT This research study addresses the limitations of the GloVe (Global Vectors for Word Representation) algorithm in the context of extractive text summarization, focusing on mitigating sparsity issues and enhancing contextual representation. The study begins by identifying three key challenges faced by GloVe: sparsity issues impacting representation accuracy, high computational demands, and difficulties in capturing contextual semantics. Firstly, the study introduces methods to mitigate sparsity issues in GloVe embeddings. By focusing on handling out-of-vocabulary words and improving the representation of rare terms, the algorithm aims to provide a more comprehensive representation of the entire corpus. Techniques such as subword embeddings and adaptive learning rates employed to address this challenge effectively. Secondly, to address the computational intensity and memory requirements of GloVe, the thesis incorporates dimensionality reduction techniques, specifically t-distributed Stochastic Neighbor Embedding (t-SNE). By reducing the dimensionality of the word embeddings, the algorithm achieves significant improvements in processing speed and memory efficiency without sacrificing summarization quality. Finally, the study enhances the contextual representation learned by GloVe for text summarization purposes. By weighing rare words and giving them better representation, the algorithm improves its ability to capture contextual semantics, thereby enhancing the quality of extractive text summarization. Through a series of experiments and evaluations using real-world news article datasets, the proposed enhancements are thoroughly validated. The results demonstrate notable improvements in the summarization performance of the enhanced GloVe algorithm compared to traditional GloVe implementations. The findings of this thesis contribute to advancing the state-of-the-art in extractive text summarization techniques and provice valuable insights for future research in natural language processing and machine learning.

There are no comments for this item.

to post a comment.