Research about Automatic Text Summarization Based on Discourse Structure of Chinese

Zhang, Mei Na; Fu, Wei

doi:10.4028/www.scientific.net/amr.945-949.3323

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nong et al [7] proposed to incorporate replication mechanism and input-feeding method into seq2seq architecture to improve the accuracy of model generation summary. Feng et al [8] fused RNN and CNN network structures to construct a dual-encoding network structure, which adequately encoded the source text, enabling decoding to obtain enough information to improve the accuracy of automatic summary.…”

Section: Related Workmentioning

confidence: 99%

Abstractive text summarization model based on BERT vectorization and bidirectional decoding

Teng,

Qiang,

Wang

et al. 2023

International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023)

View full text Add to dashboard Cite

Facing the pressure of the extremely inflated network information and data overload surplus, it is extremely important to locate “valuable information” efficiently and accurately. Text summarization technology in the field of Natural Language Processing (NLP) is an effective means to analyze and process network information. In this paper, we propose an abstractive text summarization model based on bidirectional encoder representations from transformers (BERT) vectorization and bidirectional decoding. The BERT is adopted to obtain a more global vector representation, which helps the subsequent encoder and decoder to fuse the full-text information to generate a summary with high generality. The decoding phase adopts a bidirectional decoding structure and combines the attention mechanism to maintain the bilateral decoding result to generate summaries. The bidirectional decoding structure can be fine-tuned according to the bidirectional results, which can overcome the tilt problem of the unidirectional structure, and the generated summaries are more consistent. The experimental results on the NLPCC2017 text summarization dataset show that the summaries generated by our model have the higher coherence at the word and sentence level, and the stronger generalization of the full text.

show abstract

Section: Related Workmentioning

confidence: 99%