Xinran Zhao

I am a second year master student majoring in Computer Science at Stanford University, where I work on Natural Language Processing with Prof. Christopher Manning.

I did my bachelors at HKUST with a GPA of 3.958 (top 1%) and have received the Academic Achievement Medal and First Class Honors. At HKUST, I was fortunate to work on commonsense reasoning, pronoun coreference resolution, hate speech detection, and knowledge graph mining with Prof. Yangqiu Song. I also worked closely with Prof. Dit-Yan Yeung on text simplification and an AI-supported online education platform.

During my exchange at Cornell University, I started my journey in NLP from debate argument mining and received great help and guidance from Prof. Claire Cardie.

I am actively looking for a Ph.D. position in NLP. I love to discuss new ideas. Do email me to start a chat.

Email  /  CV  /  Linkedin  /  GitHub  /  Google Scholar

profile photo

I am interested in working on meaningful research on natural language processing (NLP) and machine learning. My goal is to build effetive and faithful systems to tackle the great ambiguity of natural languages.

Some interesting directions I am thinking of:
(1) using retrieval-based method to improve the temporal and visual awareness of semi-parametric language models;
(2) checking the robustness and interpretability of large language models with datasets formatted beyond simple lists of text sequences (e.g., with meaningful innate connections across instances);
(3) leveraging compositionality to manipulate (e.g., compressing or decorating) natural language datasets.

1. On Measuring the Intrinsic Few-Shot Hardness of Datasets
Xinran Zhao*, Shikhar Murty*, and Christopher Manning (*: equal contribution)
In Proceedings of EMNLP 2022 (to appear).
2. Weakly Supervised Text Classification using Supervision Signals from a Language Model
Ziqian Zeng, Weimin Nie, Tianqing Fang, Xiang Li, Xinran Zhao, and Yangqiu Song
In Findings of NAACL 2022. [details] 
3. PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution
Xinran Zhao, Hongming Zhang, and Yangqiu Song
In Proceedings of LREC 2022. [paper] /  [details] 
4. Leveraging Topic Relatedness for Argument Persuasion
Xinran Zhao, Esin Durmus, Hongming Zhang, and Claire Cardie
In Findings of ACL 2021. [details] 
5. Probing Toxic Content in Large Pre-Trained Language Models
Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, and Dit-Yan Yeung
In Proceedings of ACL 2021. [details] 
6. WinoWhy: A Deep Diagnose of Essential Commonsense Knowledge for Answering Winograd Schema Challenge
Xinran Zhao*, Hongming Zhang*, and Yangqiu Song (*: equal contribution)
In Proceedings of ACL 2020.
[paper] /  [code & data] /  [details] 
7. A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution
Hongming Zhang, Xinran Zhao, and Yangqiu Song
In CRAC @ EMNLP 2021.
[paper] /  [code & data] /  [details] 
8. Learning Contextual Causality Between Daily Events from Time-consecutive Images
Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, and Dan Roth
In Causality in Vision @ CVPR 2021. [details] 
9. The Effects of Fear of Missing Out on Social Media Posting Preferences
Yue Xi, Jiale Huo, Xinran Zhao, Yushi Jiang, Qiang Yang
To appear in European Journal of Marketing.
under submission
1. Towards Adaptive Knowledge Usage for NLP Tasks
Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, and Jianshu Chen
To be submitted to a top-tier natural language processing coference.
2. Towards Reference-free Text Simplification Evaluation
Xinran Zhao, Dit-Yan Yeung
To be submitted to a top-tier natural language processing coference.
3. EPIC-States: A Benchmark on Understanding Object State Change
Xiang Li, Jiangwei Yu, Xinran Zhao, Hongming Zhang, and Yu-Xiong Wang
Submitted to a top-tier computer vision coference.
4. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (BIG-bench)
Aarohi Srivastava et al (100+ authors), Xinran Zhao
Submitted to TMLR
Academic Events

  • Invited to serve as a Program Committee Member for AAAI 2023.
  • Invited to give a talk (topic: On Task Difficulty of Few-shot Learning) for ICML 2022 Commonsense Tutorial.
  • Invited to serve as a reviewer for EMNLP 2022.
  • Invited to serve as an emergent reviewer for ECCV 2022.
  • Projects
    1. Seek to Embed ASER: A Large-scale Eventuality Knowledge Graph
    Advised by Xin Liu and Prof. Yangqiu Song
    An acknowledged contributor (paper was accepted by WWW 2020). [paper] /  [details] 
    2. An Online Learning Platform with NLP Supported Teaching Assistant
    Advised by Prof. Dit-Yan Yeung.
    Final Year Project. [details] 
    3. A Comparative Study on the Sentimental Characteristics of Chinese and Western Tourists
    Advised by Xi Yue and Prof. Yushi Jiang
    In Annual Conference of Journal of Marketing Science 2019, China.
    [paper (Chinese)] /  [paper (English)] /  [details] 
    4. One-shot Pokemon Classification
    Advised by Prof. Qifeng Chen.
    Cousework. [report]  [details] 

    Besides researching, I am also keen on other activities:

  • I am an enthusiastic body-builder that can do 140 kg squat.

  • I am a member of HKUST Mandarin Debate team, where we won the First Prize for Bayarea Debate Championship and Top 8 for the sixth and seventh International Madarin Debate Invitational in Singapore.

  • I am a traditional Chinese poem writer who got a few publishments on newspapers.

  • I am an active member of the HKUST Archery Club.

  • This page is forked from Jon Barron's home page.