Yukun Ma’s Home Page


Yukun Ma’s Home Page

I’m currently a senior specialist in AIR Labs of Continental Automotive Group. I got my PhD from NTU in the year 2018. I was also a Research Associate with the Rolls-Royce@NTU Corporate Lab under supervision of Erik Cambria. I have a broad interest in natural language processing including sentiment analysis, representation learning, and language modeling.

This page serves as a humble place for an updated record of my recent research and collaboration.

Selected Publication

Journal

  • Yukun Ma, Haiyun Peng, Tahir Khan, Erik Cambria, and Amir Hussain. Sentic LSTM: a hybrid network for targeted aspect-based sentiment analysis. Cognitive Computation, 10(4), 639-650.

  • Haiyun Peng, Yukun Ma, Yang Li, and Erik Cambria. “Learning multi-grained aspect target sequence for Chinese sentiment analysis.” Knowledge-Based Systems 148 (2018): 167-176.

Conference

  • Yukun Ma, Patrick H. Chen and Cho-Jui Hsieh. “MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model” to appear in Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019). [Equal Contribution]

  • Tianyu Li, Chien-Chih Wang, Yukun Ma, Patricia Ortal, Qifang Zhao, Bjorn Stenger and Yu Hirate. “Learning Classifiers on Positive and Unlabeled Data with Policy Gradient”, to appear in The 19th IEEE International Conference on Data Mining (ICDM 2019)

  • Tianyu Li, Yukun Ma, Jiu Xu, Bjorn Stenger, Chen Liu, and Yu Hirate. Deep Heterogeneous Autoencoders for Collaborative Filtering. In 2018 IEEE International Conference on Data Mining (ICDM 2018) (pp. 1164-1169). IEEE.

  • Yukun Ma, Haiyun Peng, and Erik Cambria. “Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM.” Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018). 2018.

  • Yukun Ma, Erik Cambria, and Sa Gao. “Label embedding for zero-shot fine-grained named entity typing.” In the 26th International Conference on Computational Linguistics: Technical Papers (COLING 2016), pp. 171-180. 2016.

  • Yukun Ma, Jung-jae Kim, Benjamin Bigot, and Tahir Muhammad Khan. “Feature-enriched word embeddings for named entity recognition in open-domain conversations.” In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), pp. 6055-6059. IEEE, 2016.

Service

Invited Journal Reviewer

  • IEEE Trans. Affective Computing
  • IEEE CIM
  • IEEE Access
  • Artificial Intelligence Review
  • Information Fusion
  • Knowledge-based System

    PC Member

  • NAACL 2019
  • AAAI 2019
  • AAAI 2020