Yixin Nie(聂意新) Research Scientist @ Meta AI yixin1 [at] cs.unc.edu Github | Google Scholar | CV

About Me

I am a Research Scientist at Meta AI. I did my Ph.D. in Computer Science Department at University of North Carolina at Chapel Hill, advised by Mohit Bansal. Before that, I did my undergraduate degree at China University of Geosciences, and then my master's degree at The University of Chicago.

My work focuses on machine learning and natural language processing. My research interests are sparked from the idea of natural language acquisition for machine.

News

Experience

Publications [Google Scholar]

TVLT: Textless Vision-Language Transformer [code]
Zineng Tang*, Jaemin Cho*, Yixin Nie*, Mohit Bansal
NeurIPS 2022 (Oral), New Orlean, LA.

MLP Architectures for Vision-and-Language Modeling: An Empirical Study
Yixin Nie*, Linjie Li*, Zhe Gan, Shuohang Wang, Chenguang Zhu, Michael Zeng, Zicheng Liu, Mohit Bansal, Lijuan Wang
ArXiv.

Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning [code&data]
Xiang Zhou*, Yixin Nie*, Mohit Bansal
Findings of ACL 2022.

To What Extent Do Human Explanations of Model Behavior Align with Actual Model Behavior?
Grusha Prasad, Yixin Nie, Mohit Bansal, Robin Jia, Douwe Kiela, Adina Williams
BlackboxNLP workshop, EMNLP 2021.

I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling [data]
Yixin Nie, Mary Williamson, Mohit Bansal, Douwe Kiela, Jason Weston
ACL 2021.

Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference [data]
Hai Hu, He Zhou, Zuoyu Tian, Yiwen Zhang, Yina Ma, Yanting Li, Yixin Nie, Kyle Richardson
Findings of ACL 2021.

Dynabench: Rethinking Benchmarking in NLP [github][website][Facebook AI Blog]
Douwe Kiela, Max Bartolo, Yixin Nie, Divyansh Kaushik, Atticus Geiger, Zhengxuan Wu, Bertie Vidgen, Grusha Prasad, Amanpreet Singh, Pratik Ringshia, Zhiyi Ma, Tristan Thrush, Sebastian Riedel, Zeerak Waseem, Pontus Stenetorp, Robin Jia, Mohit Bansal, Christopher Potts, Adina Williams
NAACL 2021.

What Can We Learn from Collective Human Opinions on Natural Language Inference Data? [code&data][slides]
Yixin Nie, Xiang Zhou, Mohit Bansal
EMNLP 2020.

ConjNLI: Natural Language Inference Over Conjunctive Sentences [code&data]
Swarnadeep Saha, Yixin Nie, Mohit Bansal
EMNLP 2020.

The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions [code]
Xiang Zhou, Yixin Nie, Hao Tan, Mohit Bansal
EMNLP 2020.

Adversarial NLI: A New Benchmark for Natural Language Understanding [code&data] [slides] [demo]
Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, Douwe Kiela
ACL 2020, Seattle, WA.

Simple Compounded-Label Training for Fact Extraction and Verification
Yixin Nie*, Lisa Bauer*, and Mohit Bansal,
Fact Extraction and Verification (FEVER) workshop, ACL 2020, Seattle, WA.

Revealing the Importance of Semantic Retrieval for Machine Reading at Scale [code] [poster]
Yixin Nie, Songhe Wang, Mohit Bansal
EMNLP 2019, Hong Kong, China.
Results on HotpotQA Leaderboard.

Combining Fact Extraction and Verification with Neural Semantic Matching Networks [code] [slides] [Press Article]
Yixin Nie, Haonan Chen, Mohit Bansal
AAAI 2019, Honolulu, Hawaii.
The Top One Model at Fact Extraction and Verification (FEVER) Workshop, EMNLP 2018, Brussels, Belgium.

Analyzing Compositionality-Sensitivity of NLI Models [code] [slides]
Yixin Nie*, Yicheng Wang*, Mohit Bansal
AAAI 2019, Honolulu, Hawaii.

Shortcut-Stacked Sentence Encoders for Multi-Domain Inference [code] [slides]
Yixin Nie and Mohit Bansal
RepEval Workshop, EMNLP 2017, Copenhagen, Denmark.
The Top Single Model in RepEval Shared Task.

Teaching

Teaching Assistant, Graduate Natural Language Processing, UNC Chapel Hill, Fall 2017.
Teaching Assistant, Algorithms and Analysis, UNC Chapel Hill, Fall 2017.

Misc.

My hometown is Wuhan.
Suprisingly, I always find writing much more interesting than coding.