JIPS (Çѱ¹Á¤º¸Ã³¸®ÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Document Summarization Model Based on General Context in RNN |
¿µ¹®Á¦¸ñ(English Title) |
Document Summarization Model Based on General Context in RNN |
ÀúÀÚ(Author) |
Jinjuan Wu
Zhengtao Yu
Shulong Liu
Yafei Zhang
Shengxiang Gao
Heechan Kim
Soowon Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 15 NO. 06 PP. 1378 ~ 1391 (2019. 12) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
In recent years, automatic document summarization has been widely studied in the field of natural language processing thanks to the remarkable developments made using deep learning models. To decode a word, existing models for abstractive summarization usually represent the context of a document using the weighted hidden states of each input word when they decode it. Because the weights change at each decoding step, these weights reflect only the local context of a document. Therefore, it is difficult to generate a summary that reflects the overall context of a document. To solve this problem, we introduce the notion of a general context and propose a model for summarization based on it. The general context reflects overall context of the document that is independent of each decoding step. Experimental results using the CNN/Daily Mail dataset show that the proposed model outperforms existing models.
|
Å°¿öµå(Keyword) |
Bilingual News
Chinese-Vietnamese
Sentence Simil
Summarizing the Difference
Undirected Graph
Document Summarization
General Context
Natural Language Processing
Sequence-to-Sequence Model
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|