International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 175 - Issue 20 |
Published: Sep 2020 |
Authors: Kaushal Raj Mishra, Jayshree Rathi, Janardan Banjara |
![]() |
Kaushal Raj Mishra, Jayshree Rathi, Janardan Banjara . Encoder Decoder based Nepali News Headline Generation. International Journal of Computer Applications. 175, 20 (Sep 2020), 1-4. DOI=10.5120/ijca2020920735
@article{ 10.5120/ijca2020920735, author = { Kaushal Raj Mishra,Jayshree Rathi,Janardan Banjara }, title = { Encoder Decoder based Nepali News Headline Generation }, journal = { International Journal of Computer Applications }, year = { 2020 }, volume = { 175 }, number = { 20 }, pages = { 1-4 }, doi = { 10.5120/ijca2020920735 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2020 %A Kaushal Raj Mishra %A Jayshree Rathi %A Janardan Banjara %T Encoder Decoder based Nepali News Headline Generation%T %J International Journal of Computer Applications %V 175 %N 20 %P 1-4 %R 10.5120/ijca2020920735 %I Foundation of Computer Science (FCS), NY, USA
In this paper, a method for Nepali News Headline Generation is presented. The proposed method uses GRUs, in an encoder-decoder fashion, taking the news content as input and generating a headline as the output. The news is converted into word tokens, which are vectorized using FastText, trained on a corpus of Nepali news articles and headlines collected from several web portals. The headline generation model is also trained on the same corpus. A sequence to sequence model, with an encoder and a decoder GRU is used as the generation model. The model was able to attain a BLEU score of 22.1 on the test set.