A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM

Nishat Tasnim Ahmed Meem; Muhammad Mahir Hasan Chowdhury; Md Mahfuzur Rahman

doi:10.1109/ICCIT48885.2019.9038242

A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM

Nishat Tasnim Ahmed Meem, Muhammad Mahir Hasan Chowdhury, Md Mahfuzur Rahman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Keyphrases are single or multiple word phrases of a document which describe the principal topics of that document. These keyphrases help readers to get an overview of the document. In this paper, we proposed a system that uses the combination of Convolutional Neural Network and Bidirectional Long Short-Term Memory (BiLSTM) Recurrent Neural Network (RNN) to automatically detect keyphrases from a document. We also used some preprocessing steps to clean and generate candidates keyphrases to train the model. Convolutional Neural Network can analyze semantic meanings of sentences. Bidirectional LSTM can learn the relations among words in the sentences. A Bengali pre-trained word embedding is used in this work.

Original language	English
Title of host publication	2019 22nd International Conference on Computer and Information Technology, ICCIT 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728158426
DOIs	https://doi.org/10.1109/ICCIT48885.2019.9038242
State	Published - Dec 2019
Externally published	Yes

Publication series

Name	2019 22nd International Conference on Computer and Information Technology, ICCIT 2019

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

BiL- STM
CNN
Convolutional Neural Network
FastText
Keyphrase Extraction
Neural Network
RNN
Word Embedding

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

Access to Document

10.1109/ICCIT48885.2019.9038242

Cite this

Ahmed Meem, N. T., Chowdhury, M. M. H., & Rahman, M. M. (2019). A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM. In 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019 Article 9038242 (2019 22nd International Conference on Computer and Information Technology, ICCIT 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCIT48885.2019.9038242

Ahmed Meem, Nishat Tasnim ; Chowdhury, Muhammad Mahir Hasan ; Rahman, Md Mahfuzur. / A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM. 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 22nd International Conference on Computer and Information Technology, ICCIT 2019).

@inproceedings{361454e7b7d64c83b5428fe89708d3f5,

title = "A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM",

abstract = "Keyphrases are single or multiple word phrases of a document which describe the principal topics of that document. These keyphrases help readers to get an overview of the document. In this paper, we proposed a system that uses the combination of Convolutional Neural Network and Bidirectional Long Short-Term Memory (BiLSTM) Recurrent Neural Network (RNN) to automatically detect keyphrases from a document. We also used some preprocessing steps to clean and generate candidates keyphrases to train the model. Convolutional Neural Network can analyze semantic meanings of sentences. Bidirectional LSTM can learn the relations among words in the sentences. A Bengali pre-trained word embedding is used in this work.",

keywords = "BiL- STM, CNN, Convolutional Neural Network, FastText, Keyphrase Extraction, Neural Network, RNN, Word Embedding",

author = "\{Ahmed Meem\}, \{Nishat Tasnim\} and Chowdhury, \{Muhammad Mahir Hasan\} and Rahman, \{Md Mahfuzur\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.",

year = "2019",

month = dec,

doi = "10.1109/ICCIT48885.2019.9038242",

language = "English",

series = "2019 22nd International Conference on Computer and Information Technology, ICCIT 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 22nd International Conference on Computer and Information Technology, ICCIT 2019",

address = "United States",

}

Ahmed Meem, NT, Chowdhury, MMH & Rahman, MM 2019, A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM. in 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019., 9038242, 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ICCIT48885.2019.9038242

A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM. / Ahmed Meem, Nishat Tasnim; Chowdhury, Muhammad Mahir Hasan; Rahman, Md Mahfuzur.
2019 22nd International Conference on Computer and Information Technology, ICCIT 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9038242 (2019 22nd International Conference on Computer and Information Technology, ICCIT 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM

AU - Ahmed Meem, Nishat Tasnim

AU - Chowdhury, Muhammad Mahir Hasan

AU - Rahman, Md Mahfuzur

PY - 2019/12

Y1 - 2019/12

N2 - Keyphrases are single or multiple word phrases of a document which describe the principal topics of that document. These keyphrases help readers to get an overview of the document. In this paper, we proposed a system that uses the combination of Convolutional Neural Network and Bidirectional Long Short-Term Memory (BiLSTM) Recurrent Neural Network (RNN) to automatically detect keyphrases from a document. We also used some preprocessing steps to clean and generate candidates keyphrases to train the model. Convolutional Neural Network can analyze semantic meanings of sentences. Bidirectional LSTM can learn the relations among words in the sentences. A Bengali pre-trained word embedding is used in this work.

AB - Keyphrases are single or multiple word phrases of a document which describe the principal topics of that document. These keyphrases help readers to get an overview of the document. In this paper, we proposed a system that uses the combination of Convolutional Neural Network and Bidirectional Long Short-Term Memory (BiLSTM) Recurrent Neural Network (RNN) to automatically detect keyphrases from a document. We also used some preprocessing steps to clean and generate candidates keyphrases to train the model. Convolutional Neural Network can analyze semantic meanings of sentences. Bidirectional LSTM can learn the relations among words in the sentences. A Bengali pre-trained word embedding is used in this work.

KW - BiL- STM

KW - CNN

KW - Convolutional Neural Network

KW - FastText

KW - Keyphrase Extraction

KW - Neural Network

KW - RNN

KW - Word Embedding

UR - https://www.scopus.com/pages/publications/85082999075

U2 - 10.1109/ICCIT48885.2019.9038242

DO - 10.1109/ICCIT48885.2019.9038242

M3 - Conference contribution

AN - SCOPUS:85082999075

T3 - 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019

BT - 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ahmed Meem NT, Chowdhury MMH, Rahman MM. A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM. In 2019 22nd International Conference on Computer and Information Technology, ICCIT 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9038242. (2019 22nd International Conference on Computer and Information Technology, ICCIT 2019). doi: 10.1109/ICCIT48885.2019.9038242

A machine learning approach to extract keyphrases from bengali document using CNN-Bidirectional LSTM

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this