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 Xian Li

Xian Li

Efficient Large Scale Language Modeling with Mixtures of Experts


Dec 20, 2021
Mikel Artetxe, Shruti Bhosale, Naman Goyal, Todor Mihaylov, Myle Ott, Sam Shleifer, Xi Victoria Lin, Jingfei Du, Srinivasan Iyer, Ramakanth Pasunuru, Giri Anantharaman, Xian Li, Shuohui Chen, Halil Akin, Mandeep Baines, Louis Martin, Xing Zhou, Punit Singh Koura, Brian O'Horo, Jeff Wang, Luke Zettlemoyer, Mona Diab, Zornitsa Kozareva, Ves Stoyanov

Figure 1 for Efficient Large Scale Language Modeling with Mixtures of Experts
Figure 2 for Efficient Large Scale Language Modeling with Mixtures of Experts
Figure 3 for Efficient Large Scale Language Modeling with Mixtures of Experts
Figure 4 for Efficient Large Scale Language Modeling with Mixtures of Experts

  Access Paper or Ask Questions

Few-shot Learning with Multilingual Language Models


Dec 20, 2021
Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O'Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov, Xian Li

Figure 1 for Few-shot Learning with Multilingual Language Models
Figure 2 for Few-shot Learning with Multilingual Language Models
Figure 3 for Few-shot Learning with Multilingual Language Models
Figure 4 for Few-shot Learning with Multilingual Language Models
* 36 pages 
  Access Paper or Ask Questions

Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs


Nov 26, 2021
Peter Hase, Mona Diab, Asli Celikyilmaz, Xian Li, Zornitsa Kozareva, Veselin Stoyanov, Mohit Bansal, Srinivasan Iyer

Figure 1 for Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
Figure 2 for Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
Figure 3 for Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
Figure 4 for Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
* 19 pages 
  Access Paper or Ask Questions

Energy-Efficient Online Data Sensing and Processing in Wireless Powered Edge Computing Systems


Nov 04, 2021
Xian Li, Suzhi Bi, Yuan Zheng, Hui Wang

Figure 1 for Energy-Efficient Online Data Sensing and Processing in Wireless Powered Edge Computing Systems
Figure 2 for Energy-Efficient Online Data Sensing and Processing in Wireless Powered Edge Computing Systems
Figure 3 for Energy-Efficient Online Data Sensing and Processing in Wireless Powered Edge Computing Systems
Figure 4 for Energy-Efficient Online Data Sensing and Processing in Wireless Powered Edge Computing Systems
* This article has been submitted to IEEE for possible publication.Copyright may be transferred without notice, after which this version may no longer be accessible 
  Access Paper or Ask Questions

Distributionally Robust Multilingual Machine Translation


Sep 09, 2021
Chunting Zhou, Daniel Levy, Xian Li, Marjan Ghazvininejad, Graham Neubig

Figure 1 for Distributionally Robust Multilingual Machine Translation
Figure 2 for Distributionally Robust Multilingual Machine Translation
Figure 3 for Distributionally Robust Multilingual Machine Translation
Figure 4 for Distributionally Robust Multilingual Machine Translation
* Long paper accepted by EMNLP2021 main conference 
  Access Paper or Ask Questions

FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task


Aug 14, 2021
Yun Tang, Hongyu Gong, Xian Li, Changhan Wang, Juan Pino, Holger Schwenk, Naman Goyal

Figure 1 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Figure 2 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Figure 3 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Figure 4 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
* Accepted by IWSLT 2021 as a system paper 
  Access Paper or Ask Questions

Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task


Jul 12, 2021
Yun Tang, Juan Pino, Xian Li, Changhan Wang, Dmitriy Genzel

Figure 1 for Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
Figure 2 for Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
Figure 3 for Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
Figure 4 for Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
* Accepted by ACL 2021 
  Access Paper or Ask Questions

Unaware Fairness: Hierarchical Random Forest for Protected Classes


Jun 30, 2021
Xian Li

Figure 1 for Unaware Fairness: Hierarchical Random Forest for Protected Classes
Figure 2 for Unaware Fairness: Hierarchical Random Forest for Protected Classes
Figure 3 for Unaware Fairness: Hierarchical Random Forest for Protected Classes
Figure 4 for Unaware Fairness: Hierarchical Random Forest for Protected Classes

  Access Paper or Ask Questions

Online Cognitive Data Sensing and Processing Optimization in Energy-harvesting Edge Computing Systems


Jun 27, 2021
Xian Li, Suzhi Bi, Zhi Quan, Hui Wang

Figure 1 for Online Cognitive Data Sensing and Processing Optimization in Energy-harvesting Edge Computing Systems
Figure 2 for Online Cognitive Data Sensing and Processing Optimization in Energy-harvesting Edge Computing Systems
Figure 3 for Online Cognitive Data Sensing and Processing Optimization in Energy-harvesting Edge Computing Systems
Figure 4 for Online Cognitive Data Sensing and Processing Optimization in Energy-harvesting Edge Computing Systems
* This paper has been submitted for potential journal publication 
  Access Paper or Ask Questions

Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling


Jun 21, 2021
Hongyu Gong, Yun Tang, Juan Pino, Xian Li

Figure 1 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Figure 2 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Figure 3 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Figure 4 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling

  Access Paper or Ask Questions

Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation


Jun 01, 2021
Adithya Renduchintala, Denise Diaz, Kenneth Heafield, Xian Li, Mona Diab

Figure 1 for Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
Figure 2 for Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
Figure 3 for Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
Figure 4 for Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
* Accepted at ACL 2021 
  Access Paper or Ask Questions

Demystify Optimization Challenges in Multilingual Transformers


Apr 20, 2021
Xian Li, Hongyu Gong

Figure 1 for Demystify Optimization Challenges in Multilingual Transformers
Figure 2 for Demystify Optimization Challenges in Multilingual Transformers
Figure 3 for Demystify Optimization Challenges in Multilingual Transformers
Figure 4 for Demystify Optimization Challenges in Multilingual Transformers

  Access Paper or Ask Questions

Adaptive Sparse Transformer for Multilingual Translation


Apr 15, 2021
Hongyu Gong, Xian Li, Dmitriy Genzel

Figure 1 for Adaptive Sparse Transformer for Multilingual Translation
Figure 2 for Adaptive Sparse Transformer for Multilingual Translation
Figure 3 for Adaptive Sparse Transformer for Multilingual Translation
Figure 4 for Adaptive Sparse Transformer for Multilingual Translation

  Access Paper or Ask Questions

On the Subbagging Estimation for Massive Data


Feb 28, 2021
Tao Zou, Xian Li, Xuan Liang, Hansheng Wang

Figure 1 for On the Subbagging Estimation for Massive Data
Figure 2 for On the Subbagging Estimation for Massive Data
Figure 3 for On the Subbagging Estimation for Massive Data
Figure 4 for On the Subbagging Estimation for Massive Data

  Access Paper or Ask Questions

Improving Zero-Shot Translation by Disentangling Positional Information


Dec 30, 2020
Danni Liu, Jan Niehues, James Cross, Francisco Guzmán, Xian Li

Figure 1 for Improving Zero-Shot Translation by Disentangling Positional Information
Figure 2 for Improving Zero-Shot Translation by Disentangling Positional Information
Figure 3 for Improving Zero-Shot Translation by Disentangling Positional Information
Figure 4 for Improving Zero-Shot Translation by Disentangling Positional Information

  Access Paper or Ask Questions

Towards Understanding the Optimal Behaviors of Deep Active Learning Algorithms


Dec 29, 2020
Yilun Zhou, Adi Renduchintala, Xian Li, Sida Wang, Yashar Mehdad, Asish Ghoshal

Figure 1 for Towards Understanding the Optimal Behaviors of Deep Active Learning Algorithms
Figure 2 for Towards Understanding the Optimal Behaviors of Deep Active Learning Algorithms
Figure 3 for Towards Understanding the Optimal Behaviors of Deep Active Learning Algorithms
Figure 4 for Towards Understanding the Optimal Behaviors of Deep Active Learning Algorithms
* 17 pages, 17 figures 
  Access Paper or Ask Questions

Cross-Modal Transfer Learning for Multilingual Speech-to-Text Translation


Oct 24, 2020
Chau Tran, Changhan Wang, Yuqing Tang, Yun Tang, Juan Pino, Xian Li

Figure 1 for Cross-Modal Transfer Learning for Multilingual Speech-to-Text Translation
Figure 2 for Cross-Modal Transfer Learning for Multilingual Speech-to-Text Translation
Figure 3 for Cross-Modal Transfer Learning for Multilingual Speech-to-Text Translation
Figure 4 for Cross-Modal Transfer Learning for Multilingual Speech-to-Text Translation

  Access Paper or Ask Questions

DeFuzz: Deep Learning Guided Directed Fuzzing


Oct 23, 2020
Xiaogang Zhu, Shigang Liu, Xian Li, Sheng Wen, Jun Zhang, Camtepe Seyit, Yang Xiang

Figure 1 for DeFuzz: Deep Learning Guided Directed Fuzzing
Figure 2 for DeFuzz: Deep Learning Guided Directed Fuzzing
Figure 3 for DeFuzz: Deep Learning Guided Directed Fuzzing
Figure 4 for DeFuzz: Deep Learning Guided Directed Fuzzing

  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

Multilingual Translation with Extensible Multilingual Pretraining and Finetuning


Aug 02, 2020
Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan

Figure 1 for Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
Figure 2 for Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
Figure 3 for Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
Figure 4 for Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
* 10 pages (main) + 5 pages (appendices). 9 tables and 2 figures 
  Access Paper or Ask Questions

AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types


Jun 24, 2020
Xin Luna Dong, Xiang He, Andrey Kan, Xian Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, Saurabh Deshpande, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum, Jiawei Han

Figure 1 for AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
Figure 2 for AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
Figure 3 for AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
Figure 4 for AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types
* KDD 2020 
  Access Paper or Ask Questions

Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data


Jun 23, 2020
Yaqing Wang, Yifan Ethan Xu, Xian Li, Xin Luna Dong, Jing Gao

Figure 1 for Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
Figure 2 for Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
Figure 3 for Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
Figure 4 for Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
* KDD 2020 
  Access Paper or Ask Questions

Cross-lingual Retrieval for Iterative Self-Supervised Training


Jun 16, 2020
Chau Tran, Yuqing Tang, Xian Li, Jiatao Gu

Figure 1 for Cross-lingual Retrieval for Iterative Self-Supervised Training
Figure 2 for Cross-lingual Retrieval for Iterative Self-Supervised Training
Figure 3 for Cross-lingual Retrieval for Iterative Self-Supervised Training
Figure 4 for Cross-lingual Retrieval for Iterative Self-Supervised Training

  Access Paper or Ask Questions

Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation


Apr 30, 2020
Asa Cooper Stickland, Xian Li, Marjan Ghazvininejad

Figure 1 for Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation
Figure 2 for Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation
Figure 3 for Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation
Figure 4 for Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation

  Access Paper or Ask Questions

Multilingual Denoising Pre-training for Neural Machine Translation


Jan 23, 2020
Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer

Figure 1 for Multilingual Denoising Pre-training for Neural Machine Translation
Figure 2 for Multilingual Denoising Pre-training for Neural Machine Translation
Figure 3 for Multilingual Denoising Pre-training for Neural Machine Translation
Figure 4 for Multilingual Denoising Pre-training for Neural Machine Translation
* Work in progress 
  Access Paper or Ask Questions

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow


Oct 09, 2019
Xuezhe Ma, Chunting Zhou, Xian Li, Graham Neubig, Eduard Hovy

Figure 1 for FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Figure 2 for FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Figure 3 for FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Figure 4 for FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
* EMNLP 2019 
 * Accepted by EMNLP 2019 (Long Paper) 
  Access Paper or Ask Questions