Sentence Generation using LSTM Based Deep Learning

被引：0

作者：

Das, Sunanda ^{[1
]}

Partha, Sajal Basak ^{[1
]}

Hasan, Kazi Nasim Imtiaz ^{[1
]}

机构：

[1] Khulna Univ Engn & Technol, Dept Comp Sci & Engn, Khulna 9203, Bangladesh

来源：

2020 IEEE REGION 10 SYMPOSIUM (TENSYMP) - TECHNOLOGY FOR IMPACTFUL SUSTAINABLE DEVELOPMENT | 2020年

关键词：

Sentence Generation; Long Short-Term Memory; Word Embedding;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Sentence generation serves the process of predicting relevant words in a specific sequence. The purpose of this research is to come up with a method for generating sentences while maintaining proper grammatical structure. Here, we have implemented a sentence generation system based on Long Short-Term Memory (LSTM) architecture. Our system generally follows the basics of word embedding where words from the dataset get tokenized and turned into vector forms. These vectors are then processed and passed through a Long Short-Term Memory layer. Successive words get generated from the system after each iteration. This process winds up generating relevant words to form a sentence or a passage. The results of the system are pretty convincing compared to different existing methods.

引用

页码：1070 / 1073

页数：4

共 50 条

[21] Forecasting agricultural commodities prices using deep learning-based models: basic LSTM, bi-LSTM, stacked LSTM, CNN LSTM, and convolutional LSTM
Murugesan, R.
Mishra, Eva
Krishnan, Akash Hari
INTERNATIONAL JOURNAL OF SUSTAINABLE AGRICULTURAL MANAGEMENT AND INFORMATICS, 2022, 8 (03) : 242 - 277
[22] Classification of Image and Text Data Using Deep Learning-Based LSTM Model
Yechuri, Praveen Kumar
Ramadass, Suguna
TRAITEMENT DU SIGNAL, 2021, 38 (06) : 1809 - 1817
[23] LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data
Abri, Rayan
Artuner, Harun
GAZI UNIVERSITY JOURNAL OF SCIENCE, 2022, 35 (04): : 1417 - 1431
[24] Deep Learning Based Motion Planning For Autonomous Vehicle Using Spatiotemporal LSTM Network
Bai, Zhengwei
Cai, Baigen
Wei ShangGuan
Chai, Linguo
2018 CHINESE AUTOMATION CONGRESS (CAC), 2018, : 1610 - 1614
[25] A deep learning LSTM-based approach for AMD classification using OCT images
Hamid, Laila
Elnokrashy, Amgad
Abdelhay, Ehab H.
Abdelsalam, Mohamed M.
Neural Computing and Applications, 2024, 36 (31) : 19531 - 19547
[26] Classification of Turkish News Content by Deep Learning Based LSTM Using Fasttext Model
Nergiz, Gozde
Safali, Yasar
Avaroglu, Erdinc
Erdogan, Selahaddin
2019 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP 2019), 2019,
[27] Human Activity Recognition System Using Multimodal Sensor and Deep Learning Based on LSTM
Shin, Soo-Yeun
Cha, Joo-Heon
TRANSACTIONS OF THE KOREAN SOCIETY OF MECHANICAL ENGINEERS A, 2018, 42 (02) : 111 - 121
[28] Multisource learning for skeleton-based action recognition using deep LSTM and CNN
Cui, Ran
Zhu, Aichun
Hua, Gang
Yin, Hongsheng
Liu, Haiqiang
JOURNAL OF ELECTRONIC IMAGING, 2018, 27 (04)
[29] A novel Xi’an drum music generation method based on Bi-LSTM deep reinforcement learning
Peng Li
Tian-mian Liang
Yu-mei Cao
Xiao-ming Wang
Xiao-jun Wu
Lin-yi Lei
Applied Intelligence, 2024, 54 : 80 - 94
[30] HTTP Low and Slow DoS Attack Detection using LSTM based deep learning
Gogoi, Bronjon
Ahmed, Tasiruddin
2022 IEEE 19TH INDIA COUNCIL INTERNATIONAL CONFERENCE, INDICON, 2022,

← 1 2 3 4 5 →