Morning

Some people try to find the right one, while some try to be

-
-

About Me

Hi, human / crawler!

I am Yuning Mao , a fourth-year Ph.D student in Prof. Jiawei Han's Data Mining Group, Dept. of Computer Science, University of Illinois at Urbana–Champaign (UIUC). I graduated from the IEEE Honored Class, Shanghai Jiao Tong University (SJTU).

My research centers on helping humans to acquire information and knowledge from unstructured texts more effectively and efficiently via natural language processing, machine learning, and data mining. I have experience in topics such as text summarization, question answering, semantic matching, taxonomy construction, hierarchical classification, and knowledge graph reasoning.

You can find some fun facts about me here, most of which are not in my CV (cuz I update it mainly for fun:)

What's New

[2020-10] Check out how to use constrained generation to preserve the factual consistency of abstractive summarization without worsening ROUGE [arXiv] .

[2020-09] Check out how we achieve SOTA on Natural Questions and TriviaQA using "BM25" [arXiv] .

[2020-09] Two papers on multi-document summarization and knowledge graph reasoning are accepted to EMNLP 2020.

[2020-05] Two papers on self-supervised taxonomy enrichment and knowledge collection of product knowledge graph are accepted to KDD 2020.

[2020-04] Our new metric for summarization, FAR (facet-aware evaluation) along with a detailed analysis of CNN/Daily Mail, has been accepted to ACL 2020.

[2020-04] #WWW2020 We released the first dataset on multi-document headline generation, NewSHead, along with the NHNet model in official TensorFlow repo.

-------------------------------- What's NOT new --------------------------------

[2019-03] Shared my personal collection of ✍️✍️✍️!

[2018-08-25] After being stuck in Australia for 42 days due to US visa issue, I finally got back to the states... Check out my adventure in Oz (游记)!

[2018-04-20] Birthday Gift: Paper on Taxonomy Induction is accepted to ACL 2018.

[2017-12-10] Performed at the annual carol concert in Foellinger Great Hall.

[2017-11-16] We had a concert at McKinley Presbyterian Church!

[2017-02-07] The paper "Unbiased Learning-to-Rank with Biased Feedback" in which I was acknowledged received WSDM 2017 best paper award.

What I Enjoy

Code

I enjoy coding to facilitate my (and others') life. I love both engineering work (if it's fun) and research-oriented projects. My interests lie in data mining, NLP, and broad AI. I write 🐍 cuz life is short.

To my Github
Music

My love for note ♪ is equivalent to code. I enjoy 🎤 privately (and in public). I used to play 🎻 but play 🎹 and 🎸 more often now. I also compose (very basic) music at times. I am learning blues harp!

To my recordings
Nature

I love all kinds of creatures in various sizes. Since I was a child, I have kept 🐕, 🐈, 🐓, 🦆, 🕊, 🐌, 🐛, 🕷, 🐟, 🐢, 🌸, 🌱(🍆🌶🥒...🌽🍅🍠) ... I like insects, not "bugs". I am a "professional" 🐜 keeper!

To my Ants

Selected Publications

[Google Scholar]
Ongoing / In Submission / Preprint
  1. Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen , "Generation-Augmented Retrieval for Open-domain Question Answering", 2020. [arXiv]
  2. Yuning Mao, Xiang Ren, Heng Ji, Jiawei Han, "Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation", 2020. [arXiv]
  3. Knowledge Constrained Generation, 2020
  4. Semantic Text Matching, 2020
  5. Taxonomy Enrichment, 2020
  6. Unsupervised Summarization, 2020
In Proceedings
  1. Yuning Mao, Yanru Qu, Yiqing Xie, Xiang Ren and Jiawei Han, "Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning", EMNLP 2020. [arXiv] [code]
  2. Deren Lei, Gangrong Jiang, Xiaotao Gu, Kexuan Sun, Yuning Mao and Xiang Ren, “Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning”, EMNLP 2020. [arXiv]
  3. Yuning Mao, Tong Zhao, Andrey Kan, Chenwei Zhang, Xin Luna Dong, Christos Faloutsos and Jiawei Han, "Octet: Online Catalog Taxonomy Enrichment with Self-Supervision", KDD 2020. [arXiv] [Video]
  4. Gabriel Blanco Saldana, Saurabh Deshpande, Xin Luna Dong, Xiang He, Andrey Kan, Xian Li, Yan Liang, Jun Ma, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum and Jiawei Han, "AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types", KDD 2020. [arXiv]
  5. Yuning Mao, Liyuan Liu, Qi Zhu, Xiang Ren, Jiawei Han, "Facet-Aware Evaluation for Extractive Summarization", ACL 2020. [arXiv] [code]
  6. Xiaotao Gu, Yuning Mao, Jiawei Han, Jialu Liu, You Wu, Cong Yu, Daniel Finnie, Hongkun Yu, Jiaqi Zhai, Nicholas Zukoski, "Generating Representative Headlines for News Stories", WWW 2020. [arXiv] [code]
  7. Yuning Mao, Jingjing Tian, Jiawei Han and Xiang Ren, "Hierarchical Text Classification with Reinforced Label Assignment", EMNLP 2019. [arXiv] [code]
  8. Yuning Mao, Xiang Ren, Jiaming Shen, Xiaotao Gu and Jiawei Han, "End-to-End Reinforcement Learning for Automatic Taxonomy Induction", ACL 2018. [arXiv] [code]

Selected Experience

    Work
  1. Microsoft Research, D365 AI & MSR, Weizhu Chen & Jianfeng Gao, Question Answering
  2. Amazon Research, Product Graph Team, Luna Dong, Taxonomy Construction
  3. Microsoft Research Asia, Data Mining and Enterprise Intelligence Group, Jun Yan, Relation Extraction
    Awards
  1. KDD'20 Student Registration Award 2020
  2. China National Scholarship 2015, 2016
  3. Academic Excellence Scholarship of SJTU (rank 2/72) 2016
  4. Academic Excellence Scholarship of SJTU (rank 1/72) 2015
    Review
  1. AAAI 2021, ICLR 2021
  2. AAAI 2020, ACL 2020, ICML 2020, EMNLP 2020
  3. ACL 2019, EMNLP 2019
    Sub-Review
  1. KDD 2020, WSDM 2021
  2. AAAI 2019, WWW 2019, KDD 2019, SIGIR 2019, CIKM 2019, ICDM 2019
  3. ACL 2018, CIKM 2018, ECML-PKDD 2018, IJCAI 2018, KDD 2018
  4. AKBC 2017, SDM 2017

Random Picks

img
img
img
img
img
img
img
img
img
img
img
img
img
img
img
img
img
img
img
img