Haiyue Song

Haiyue Song

Ph.D. candidate at Kyoto University.

Haiyue SONG

Ph.D student at Kyoto University. Internship researcher at NICT. Research Fellowships for Young Scientists (DC1).

Natural Language Processing and Machine Translation.

Email: song@nlp.ist.i.kyoto-u.ac.jp

Publication


Education

Kyoto University

Supervised by Professor Kurohashi at Kurohashi-Chu-Muwaraki Lab

  • Ph.D student of Intelligence Science and Technology, October 2020-present

  • Master student of Intelligence Science and Technology, October 2018-September 2020

Shanghai Jiao Tong University

Supervised by Professor Li Jiang at Advanced Computer Architecture Lab

  • Bachelor student of Computer Science and Technology, September 2014-July 2018

Nagoya University

  • Exchange student, October 2017-February 2018


Research

  • Natural language processing: low-resource/multilingual/multimodal machine translation, transfer learning, self-supervised learning, subword segmentation
  • Computer vision: image matting, semantic segmentation
  • Computer architecture: DNN acceleration, efficiency

Work experience

JSPS Research Fellowship

  • Research Fellowships for Young Scientists (DC1), April 2021-

NICT

Supervised by Fujita and Raj Dabre at ASTREC

  • Research internship, August 2020-present
  • Research internship, October 2019-November 2019

LINE

  • Internship at machine learning team, February 2019-March 2019
  • Summary Report


Publication

Google Scholar, DBLP, Research Gate, and ACL profile

Journal

  • Li Jiang, Zhuoran Song, Haiyue Song, Chengwen Xu, Qiang Xu, Naifeng Jing, Weifeng Zhang, Xiaoyao Liang.
    Energy-Efficient and Quality-Assured Approximate Computing Framework Using a Co-Training Method
    ACM Transactions on Design Automation of Electronic Systems (TODAES2019), pp.59:1-59:25, (2019.11)
    [paper], [bib]

International Conference

  • Akiko Aizawa, Frederic Bergeron, Junjie Chen, Fei Cheng, Katsuhiko Hayashi, Kentaro Inui, Hiroyoshi Ito, Daisuke Kawahara, Masaru Kitsuregawa, Hirokazu Kiyomaru, Masaki Kobayashi, Takashi Kodama, Sadao Kurohashi, Qianying Liu, Masaki Matsubara, Yusuke Miyao, Atsuyuki Morishima, Yugo Murawaki, Kazumasa Omura, Haiyue Song, Eiichiro Sumita, Shinji Suzuki, Ribeka Tanaka, Yu Tanaka, Masashi Toyoda, Nobuhiro Ueda, Honai Ueoka, Masao Utiyama, Ying Zhong (in alphabetical order).
    A System for Worldwide COVID-19 Information Aggregation
    NLP-COVID19@ACL2020 and NLP-COVID19 (part2)@EMNLP2020 [paper], [website], [code], [dataset]

  • Haiyue Song, Raj Dabre, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi and Eiichiro Sumita.
    Pre-training via Leveraging Assisting Languages for Neural Machine Translation
    Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL2020SRW), pp.279-285, Seattle, Washington, United States, (2020, 7).
    [paper], [paper (arXiv_version)], [slides], [bib]

  • Haiyue Song, Raj Dabre, Atsushi Fujita and Sadao Kurohashi.
    Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
    Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC2020), pp.3640‑3649, Marseille, France, (2020.5).
    [github repo], [paper], [bib]

  • Zhuoyuan Mao, Fabien Cromieres, Raj Dabre, Haiyue Song and Sadao Kurohashi.
    JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
    Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC2020), pp.3683‑3691, Marseille, France, (2020.5).
    [paper], [bib]

  • Haiyue Song, Chengwen Xu, Qiang Xu, Zhuoran Song, Naifeng Jing, Xiaoyao Liang, Li Jiang.
    Invocation-driven neural approximate computing with a multiclass-classifier and multiple approximators
    In Proceedings of the International Conference on Computer-Aided Design (ICCAD2018), pp.50, San Diego, CA, USA, (2018.11).
    [paper], [slides], [bib]

  • Haiyue Song, Xiang Song, Tianjian Li, Hao Dong, Naifeng Jing, Xiaoyao Liang, Li Jiang.
    A FPGA Friendly Approximate Computing Framework with Hybrid Neural Networks (Abstract Only)
    In Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA2018), pp.286, Monterey, CA, USA, (2018.2).
    [abstract], [poster], [bib]

Domestic Conference (non peer-reviewed)

  • Haiyue Song, Raj Dabre, Chenhui Chu, Sadao Kurohashi, and Eiichiro Sumita. Self-supervised Dynamic Programming Encoding for Neural Machine Translation 言語処理学会 第27回年次大会, 北九州, (2021.3).

  • Weiqi Gu, Haiyue Song, Chenhui Chu, and Sadao Kurohashi. Video-guided Machine Translation with Spatial Hierarchical Attention Network Encoder 言語処理学会 第27回年次大会, 北九州, (2021.3).

  • Haiyue Song, Raj Dabre, Atsushi Fujita, Sadao Kurohashi.
    Domain Adaptation of Neural Machine Translation through Multistage Fine-Tuning
    言語処理学会第26回年次大会, pp.461-464, 茨城, (2020.3).

  • Zhuoyuan Mao, Raj Dabre, Fabien Cromieres, Haiyue Song, 中尾 亮太, 黒橋 禎夫.
    ニューラル機械翻訳のための言語知識に基づくマルチタスク事前学習
    言語処理学会第26回年次大会, pp.1061-1064, 茨城, (2020.3).

Miscellaneous

  • Second reviewer of EMNLP2020, IJCNLP2020, WAT2020