Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning


Dec 06, 2022
Ukyo Honda, Taro Watanabe, Yuji Matsumoto

Add code

* WACV 2023 (19 pages, 9 figures) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

$N$-gram Is Back: Residual Learning of Neural Text Generation with $n$-gram Language Model


Nov 03, 2022
Huayang Li, Deng Cai, Jin Xu, Taro Watanabe

Add code

* Accepted to findings of EMNLP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adapting to Non-Centered Languages for Zero-shot Multilingual Translation


Sep 09, 2022
Zhi Qu, Taro Watanabe

Add code

* Accepted at COLING 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Visualizing the Relationship Between Encoded Linguistic Information and Task Performance


Mar 29, 2022
Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe, Lemao Liu

Add code

* Findings of ACL 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding


Nov 01, 2021
Yushi Hirose, Masashi Shimbo, Taro Watanabe

Add code

* 8 pages, 0 figures, accepted by 2021 IEEE International Conference on Big Knowledge. The copyright of this paper has been transferred to the IEEE, please comply with the copyright of the IEEE 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning


Apr 28, 2021
Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, Yuji Matsumoto

Add code

* EACL 2021 (11 pages, 3 figures; corrected the description of pseudo-caption preprocessing) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization


Apr 08, 2021
Shohei Higashiyama, Masao Utiyama, Taro Watanabe, Eiichiro Sumita

Add code

* NAACL-HLT 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection


Aug 31, 2018
Wei Wang, Taro Watanabe, Macduff Hughes, Tetsuji Nakagawa, Ciprian Chelba

Add code

* 11 pages, 2018 Third Conference on Machine Translation (WMT18) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email