Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Xiang Kong

Xiang Kong

Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade


Dec 31, 2020
Jiatao Gu, Xiang Kong

Figure 1 for Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
Figure 2 for Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
Figure 3 for Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
Figure 4 for Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
* 9 pages 
  Access Paper or Ask Questions

Incorporating a Local Translation Mechanism into Non-autoregressive Translation


Nov 12, 2020
Xiang Kong, Zhisong Zhang, Eduard Hovy

Figure 1 for Incorporating a Local Translation Mechanism into Non-autoregressive Translation
Figure 2 for Incorporating a Local Translation Mechanism into Non-autoregressive Translation
Figure 3 for Incorporating a Local Translation Mechanism into Non-autoregressive Translation
Figure 4 for Incorporating a Local Translation Mechanism into Non-autoregressive Translation
* EMNLP 2020 
  Access Paper or Ask Questions

Deep Transformers with Latent Depth


Oct 16, 2020
Xian Li, Asa Cooper Stickland, Yuqing Tang, Xiang Kong

Figure 1 for Deep Transformers with Latent Depth
Figure 2 for Deep Transformers with Latent Depth
Figure 3 for Deep Transformers with Latent Depth
Figure 4 for Deep Transformers with Latent Depth

  Access Paper or Ask Questions

SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations


Apr 27, 2020
Xiang Kong, Varun Gangal, Eduard Hovy

Figure 1 for SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
Figure 2 for SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
Figure 3 for SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
Figure 4 for SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
* ACL2020 
  Access Paper or Ask Questions

Decoupling Global and Local Representations from/for Image Generation


Apr 12, 2020
Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy

Figure 1 for Decoupling Global and Local Representations from/for Image Generation
Figure 2 for Decoupling Global and Local Representations from/for Image Generation
Figure 3 for Decoupling Global and Local Representations from/for Image Generation
Figure 4 for Decoupling Global and Local Representations from/for Image Generation
* First version of preprint. 22 pages (plus appendix), 16 figures, 5 tables. Due to arxiv size constraints, this version is using downscaled images. Please download the full-resolution version from https://vixra.org/abs/2004.0222 
  Access Paper or Ask Questions

Decompressing Knowledge Graph Representations for Link Prediction


Nov 19, 2019
Xiang Kong, Xianyang Chen, Eduard Hovy

Figure 1 for Decompressing Knowledge Graph Representations for Link Prediction
Figure 2 for Decompressing Knowledge Graph Representations for Link Prediction
Figure 3 for Decompressing Knowledge Graph Representations for Link Prediction
Figure 4 for Decompressing Knowledge Graph Representations for Link Prediction
* code has been released 
  Access Paper or Ask Questions

Generalized Data Augmentation for Low-Resource Translation


Jun 10, 2019
Mengzhou Xia, Xiang Kong, Antonios Anastasopoulos, Graham Neubig

Figure 1 for Generalized Data Augmentation for Low-Resource Translation
Figure 2 for Generalized Data Augmentation for Low-Resource Translation
Figure 3 for Generalized Data Augmentation for Low-Resource Translation
Figure 4 for Generalized Data Augmentation for Low-Resource Translation
* Accepted to ACL 2019 
  Access Paper or Ask Questions

An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation


Jan 22, 2019
Xiang Kong, Bohan Li, Graham Neubig, Eduard Hovy, Yiming Yang

Figure 1 for An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
Figure 2 for An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
Figure 3 for An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
Figure 4 for An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
* DEEP-DIAL 2019 
  Access Paper or Ask Questions

Neural Machine Translation with Adequacy-Oriented Learning


Nov 21, 2018
Xiang Kong, Zhaopeng Tu, Shuming Shi, Eduard Hovy, Tong Zhang

Figure 1 for Neural Machine Translation with Adequacy-Oriented Learning
Figure 2 for Neural Machine Translation with Adequacy-Oriented Learning
Figure 3 for Neural Machine Translation with Adequacy-Oriented Learning
Figure 4 for Neural Machine Translation with Adequacy-Oriented Learning
* AAAI 2019 
  Access Paper or Ask Questions

Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation


Sep 25, 2018
Xiang Kong, Qizhe Xie, Zihang Dai, Eduard Hovy

Figure 1 for Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
Figure 2 for Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
Figure 3 for Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
Figure 4 for Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation

  Access Paper or Ask Questions

Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints


Dec 13, 2016
Xiang Kong, Preethi Jyothi, Mark Hasegawa-Johnson

Figure 1 for Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints
Figure 2 for Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints
Figure 3 for Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints

  Access Paper or Ask Questions

Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures


Dec 13, 2016
Xiang Kong, Jeung-Yoon Choi, Stefanie Shattuck-Hufnagel

Figure 1 for Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures
Figure 2 for Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures
Figure 3 for Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures
Figure 4 for Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures
* ICASSP 2017 
 * ICASSP 2017 
  Access Paper or Ask Questions

Landmark-based consonant voicing detection on multilingual corpora


Nov 10, 2016
Xiang Kong, Xuesong Yang, Mark Hasegawa-Johnson, Jeung-Yoon Choi, Stefanie Shattuck-Hufnagel

Figure 1 for Landmark-based consonant voicing detection on multilingual corpora
Figure 2 for Landmark-based consonant voicing detection on multilingual corpora
Figure 3 for Landmark-based consonant voicing detection on multilingual corpora
Figure 4 for Landmark-based consonant voicing detection on multilingual corpora
* ready to submit to JASA-EL 
  Access Paper or Ask Questions