About me

I am Yanran Li, a second-year PhD student at PolyU (Hong Kong). My supervisor is Prof. Wenjie Li. See my resume. My research interests are mainly about language generation and general Deep Learning in NLP.

On this blog, I mostly write about Natural Language Processing, Machine Conversation, Deep Learning, and issues with R language.

Before PolyU, I got my Bachelor degree from the Centre of Information Science, School of Electronics Engineering and Computer Science (EECS), Peking University. I work with Prof. Sujian Li and Prof. Wenjie Li.


  • Tong Che*, Yanran Li*, Ruixiang Zhang*, R Devon Hjelm, Wenjie Li, Yangqiu Song, Yoshua Bengio. Maximum-Likelihood Augmented Discrete Generative Adversarial Networks. arXiv preprint 2017. * indicates equal contribution. [arXiv] [bib]


  • Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. IJCNLP 2017. To appear. [project page] [pdf] [arXiv] [dataset]

  • Jianbo Ye, Yanran Li, Zhaohui Wu, James Z. Wang, Wenjie Li and Jia Li. Determining Gains Acquired from Word Embedding Quantitatively using Discrete Distribution Clustering. ACL 2017. [pdf]

  • Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, and Akiko Aizawa. A Conditional Variational Framework for Dialog Generation. ACL 2017. [pdf] [arXiv]

  • Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei, and Yanran Li. AttSum: Joint Learning of Focusing and Summarization with Neural Attention. In Proceedings of COLING. 2016. [arXiv]

  • Tong Che*, Yanran Li*, Athul Jacob, Yoshua Bengio, and Wenjie Li. Mode Regularized Generative Adversarial Networks. ICLR 2017. * indicates equal contribution. [pdf] [arXiv] [bib]

  • Yanran Li, Wenjie Li, Fei Sun, and Sujian Li. Component-Enhanced Chinese Character Embeddings. Proceedings of EMNLP, 2015. [pdf] [bib]

  • Yanran Li, Wenjie Li, and Sujian Li. A Hierarchical Knowledge Representation for Expert Finding on Social Media. Proceedings of ACL, 2015. [pdf] [poster] [bib]

  • Yanran Li and Sujian Li. Query-focused Multi-Document Summarization: Combining a Topic Model with Graph-based Semi-supervised Learning. Proceedings of COLING, 2014. [pdf] [bib]

Book Chapters

  • Yanran Li. Natural Language Processing is Everywhere. Book Chapter. Post & Telecom Press, July 2015. [Kindle eBook]

Presentations and Invited Talks

  • 2017-05-21. Head First Generative Adversarial Networks From Theoretical View. Beijing. [slides]
  • 2017-05-05. Tackling the Graident Issues In Generative Adversarial Networks. The First CUHK Deep Learning Symposium. Hong Kong. [flyer] [slides]


As I didn’t want my about page to be a direct result of boredom, I concluded that the best way I can think of to describe myself is to list all of the things that make me happy. So in no particular order, here it goes:

Books (mostly Literatures). Arts (I also paint). Running. Family & Friends. Traveling. A good Sunday sunshine. Hand lettering. Coffee. Dancing (I used to dance). Gardening (I’d like to be my career). The smell of fresh flowers.

Pieces of my Chinese drawings and calligraphy works

Traveling photos

Traveling in Italy made my summer in 2015.

Genova is a small city with a fantastic Acquarium. Photos taken in Genova, Italy

I named this photo taken in Genova’s Acquarium, Solitude. Photos taken in Genova, Italy

Also, except Rome, one cannot miss Venice and its Burano… Photos taken in Venice, Italy

Florence is my favourite city, a flowery and charming city. I wanna make my holiday everytime here.. Photos taken in Florence, Italy

Especially the morning and the river I lived near, it reminds me of the pictures of my favourite artist, Rembrand. Photos taken in Florence, Italy Photos taken in Florence, Italy Photos taken in Florence, Italy

It’s morning. And morning is amazing. It’s when we charge into the future. When we blasted off for the moon.
Scaled the highest peak. And flew for the very first time. Morning starts, and changes everything.
It’s a clean slate. A fresh start.
So come dreamers, and trailblazers, champions. Come builders.
It’s morning, wake up, and be amazing.