Chunting Zhou

I am a research scientist at FAIR Seattle. I earned my PhD degree from Language Technologies Institute in the School of Computer Science at Carnegie Mellon University in May 2022, where I worked on Natural Lanuage Processing and was advised by Graham Neubig.

I am interested in and actively working on efficient and scalable generative models.

You can contact me at chunting.violet.zhou@gmail.com.

Google Scholar  /  Github  /  Twitter

profile photo

Publications

(Please check my Google Scholar for most recent publications.)
Towards a Unified View of Parameter-Efficient Transfer Learning
Junxian He*, Chunting Zhou*, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig
In proceedings of 8th International Conference on Learning Representations (ICLR), 2022 (Spotlight, 5%).
* equal contribution, order determined by random dice toss
OpenReview / arxiv / code



Luna: Linear Unified Nested Attention
Xuezhe Ma*, Xiang Kong*, Sinong Wang*, Chunting Zhou, Jonathan May, Hao Ma, Luke Zettlemoyer
Conference on Neural Information Processing Systems (NeurIPS), 2021
arxiv / code



Distributionally Robust Multilingual Machine Translation
Chunting Zhou*, Daniel Levy*, Xian Li, Marjan Ghazvininejad, Graham Neubig
In proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021
arxiv / code



Examining and Combating Spurious Features under Distribution Shift
Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig
International Conference on Machine Learning (ICML), 2021
arxiv / code / poster



Detecting Hallucinated Content in Conditional Neural Sequence Generation
Chunting Zhou, Graham Neubig, Jiatao Gu, Mona Diab, Paco Guzman, Luke Zettlemoyer, Marjan Ghazvininejad
Findings of the Conference of the 59th Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2021
arxiv / code / poster



Understanding Knowledge Distillation in Non-autoregressive Machine Translation
Chunting Zhou*, Jiatao Gu*, Graham Neubig
In proceedings of 8th International Conference on Learning Representations (ICLR), 2020
OpenReview



FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Xuezhe Ma*, Chunting Zhou*, Xian Li, Graham Neubig, Eduard Hovy
In proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019
* equal contribution, in alphabetical order
arxiv / code



Handling Syntactic Divergence in Low-Resource Machine Translation
Chunting Zhou, Xuezhe Ma, Junjie Hu, Graham Neubig
In proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019
arxiv / code



Density Matching for Bilingual Word Embedding
Chunting Zhou, Xuezhe Ma, Di Wang, Graham Neubig
In proceedings of the Conference on the North American Chapter of the Association for Computational Linguistics (NAACL), 2019
arxiv / code



MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
Xuezhe Ma, Chunting Zhou, Eduard Hovy
In proceedings of 7th International Conference on Learning Representations (ICLR), 2019
arxiv / code



Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations
Aditi Chaudhary, Chunting Zhou, Lori Levin, Graham Neubig, David R. Mortensen, Jaime G. Carbonell
In proceedings of Conference on Empirical Methods for Natural Language Processing (EMNLP), 2018
arxiv / code



StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing
Pengcheng Yin, Chunting Zhou, Junxian He, Graham Neubig
In proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018
arxiv / code



Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction
Chunting Zhou and Graham Neubig
In proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), 2017
arxiv / code



Morphological Inflection Generation with Multi-space Variational Encoder-Decoders
Chunting Zhou and Graham Neubig
The 2017 SIGNLL Conference on Computational Natural Language Learning (CoNLL), 2017
arxiv



Efficient methods for multi-label classification
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2015
Chonglin sun, Chunting Zhou, Bo Jin, Francis C.M. Lau
arxiv



A C-LSTM neural network for text classification
Chunting Zhou, Chonglin sun, Zhiyuan Liu, Francis C.M. Lau
arxiv



Category enhanced word embedding
Chunting Zhou, Chonglin sun, Zhiyuan Liu, Francis C.M. Lau
arxiv



Professional Services

  • Area chairs: EMNLP 2022, ACL 2023, NeurIPS 2023, EMNLP 2023, NeurIPS 2024, ICLR 2025.

  • Conference Reviewer: NAACL, ACL, EMNLP, EACL, COLING, NeurIPS, ICML, ICLR.

  • Journal Reviewer: IEEE Transactions on Multimedia, IEEE Transactions on Neural Networks and Learning Systems, Journal of Artificial Intelligence Research (JAIR)
  • Research Experience

  • Facebook AI Research, Research Intern hosted by Luke Zettlemoyer and Marjan Ghazvininejad , Summer 2020

  • Facebook AI Research, Research Intern hosted by Jiatao Gu , Summer 2019

  • Tsinghua University, Visting Student hosted by Zhiyuan Liu , Winter 2015

  • Microsoft Research Asia, Research Intern hosted by Jinhui Yuan , Nov 2013 - May 2014

  • Design and source code from Leonid Keselman's website