Xiang Kong


About me

I'm a machine learning researcher at Apple.

I got my Ph.D. from the School of Computer Science at CMU.


Deep Generative Models and Natural Langauge processing.


Luna: Linear Unified Nested Attention
Xuezhe Ma*, Xiang Kong*, Sinong Wang*, Chunting Zhou, Jonathan May, Hao Ma, Luke Zettlemoyer
(*: equal contribution)
NeurIPS 2021. [pdf]

Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
Jiatao Gu*, Xiang Kong*
(*: equal contribution)
ACL 2021 Findings. [pdf] [code release soon]

Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders
Xiang Kong, Adithya Renduchintala, James Cross, Yuqing Tang, Jiatao Gu, Xian Li
EACL 2021. [pdf]

Decoupling Global and Local Representations from/for Image Generation
Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy
ICLR 2021. [pdf] [code]

Incorporating a local translation mechanism into non-autoregressive translation
Xiang Kong*, Zhisong Zhang*, Eduard Hovy
(*: equal contribution)
EMNLP 2020. [pdf] [code]

An Empirical Exploration of Local Ordering Pre-training for Structured Learning
Zhisong Zhang, Xiang Kong, Lori Levin, Eduard Hovy
EMNLP 2020. [pdf]

Deep Transformers with Latent Depth
Xian Li, Asa Cooper Stickland, Yuqing Tang, Xiang Kong
NeurIPS 2020. [pdf]

A Two-Step Approach for Implicit Event Argument Detection
Zhisong Zhang, Xiang Kong, Zhengzhong Liu, Xuezhe Ma, Eduard Hovy
ACL 2020. [pdf]

SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
Xiang Kong*, Varun Gangal*, Eduard Hovy
(*: equal contribution)
ACL 2020. [pdf] [Data] [Leaderboard] [code]

Decompressing knowledge graph representations for link prediction
Xiang Kong*, Xianyang Chen*, Eduard Hovy
(*: equal contribution)
Preprint. [pdf] [code]

An adversarial approach to high-quality, sentiment-controlled neural dialogue generation
Xiang Kong, Bohan Li, Graham Neubig, Eduard Hovy, Yiming Yang
AAAI DEEP-DIAL 2019. [pdf]

Macow: Masked convolutional generative flow
Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy
NeurIPS 2019. [pdf] [code]

Generalized data augmentation for low-resource translation
Mengzhou Xia, Xiang Kong, Antonios Anastasopoulos, Graham Neubig
ACL 2019. [pdf]

Neural machine translation with adequacy-oriented learning
Xiang Kong, Zhaopeng Tu, Shuming Shi, Eduard Hovy, Tong Zhang
AAAI 2019. [pdf]

Fast and simple mixture of softmaxes with bpe and hybrid-lightrnn for language generation
Xiang Kong, Qizhe Xie, Zihang Dai, Eduard Hovy
AAAI 2019. [pdf] [code]