1 code implementation • 23 May 2023 • Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, Jinsong Su
We also introduce two deliberately designed test sets to verify the necessity of visual information: Ambiguous with the presence of ambiguous words, and Unambiguous in which the text context is self-contained for translation.
no code implementations • 20 Dec 2022 • Yaoming Zhu, Zewei Sun, Shanbo Cheng, Luyang Huang, Liwei Wu, Mingxuan Wang
Therefore, this paper correspondingly establishes new methods and new datasets for MMT.
no code implementations • Findings (ACL) 2022 • Luyang Huang, guocheng niu, Jiachen Liu, Xinyan Xiao, Hua Wu
To bridge the gap between image understanding and generation, we further design a novel commitment loss.
1 code implementation • NAACL 2021 • Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, Lu Wang
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization.
1 code implementation • ACL 2020 • Luyang Huang, Lingfei Wu, Lu Wang
Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive.
no code implementations • IJCNLP 2019 • Eva Sharma, Luyang Huang, Zhe Hu, Lu Wang
Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.