TY - JOUR
T1 - Enhancements of Attention-Based Bidirectional LSTM for Hybrid Automatic Text Summarization
AU - Jiang, Jiawen
AU - Zhang, Haiyang
AU - Dai, Chenxu
AU - Zhao, Qingjuan
AU - Feng, Hao
AU - Ji, Zhanlin
AU - Ganchev, Ivan
N1 - Funding Information:
This work was supported in part by the National Key Research and Development Program of China under Grant No. 2017YFE0135700 and in part by Grant No. BG05M2OP001-1.001-0003 financed by the Science and Education for Smart Growth Operational Program of Bulgaria (2014–2020) and co-financed by the European Union through the European Structural and Investment Funds.
Publisher Copyright:
© 2013 IEEE.
PY - 2021
Y1 - 2021
N2 - The automatic generation of a text summary is a task of generating a short summary for a relatively long text document by capturing its key information. In the past, supervised statistical machine learning was widely used for the Automatic Text Summarization (ATS) task, but due to its high dependence on the quality of text features, the generated summaries lack accuracy and coherence, while the computational power involved, and performance achieved, could not easily meet the current needs. This paper proposes four novel ATS models with a Sequence-to-Sequence (Seq2Seq) structure, utilizing an attention-based bidirectional Long Short-Term Memory (LSTM), with added enhancements for increasing the correlation between the generated text summary and the source text, and solving the problem of out-of-vocabulary (OOV) words, suppressing the repeated words, and preventing the spread of cumulative errors in generated text summaries. Experiments conducted on two public datasets confirmed that the proposed ATS models achieve indeed better performance than the baselines and some of the state-of-the-art models considered.
AB - The automatic generation of a text summary is a task of generating a short summary for a relatively long text document by capturing its key information. In the past, supervised statistical machine learning was widely used for the Automatic Text Summarization (ATS) task, but due to its high dependence on the quality of text features, the generated summaries lack accuracy and coherence, while the computational power involved, and performance achieved, could not easily meet the current needs. This paper proposes four novel ATS models with a Sequence-to-Sequence (Seq2Seq) structure, utilizing an attention-based bidirectional Long Short-Term Memory (LSTM), with added enhancements for increasing the correlation between the generated text summary and the source text, and solving the problem of out-of-vocabulary (OOV) words, suppressing the repeated words, and preventing the spread of cumulative errors in generated text summaries. Experiments conducted on two public datasets confirmed that the proposed ATS models achieve indeed better performance than the baselines and some of the state-of-the-art models considered.
KW - Natural language processing (NLP)
KW - attention mechanism
KW - automatic text summarization (ATS)
KW - bidirectional LSTM (Bi-LSTM)
KW - coverage mechanism
KW - mixed learning objective (MLO) function
KW - pointer network
KW - sequenceto-sequence (Seq2Seq) model
UR - http://www.scopus.com/inward/record.url?scp=85114750435&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2021.3110143
DO - 10.1109/ACCESS.2021.3110143
M3 - Article
AN - SCOPUS:85114750435
SN - 2169-3536
VL - 9
SP - 123660
EP - 123671
JO - IEEE Access
JF - IEEE Access
ER -