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 Bill Yuchen Lin

Bill Yuchen Lin

On Continual Model Refinement in Out-of-Distribution Data Streams


May 04, 2022
Bill Yuchen Lin, Sida Wang, Xi Victoria Lin, Robin Jia, Lin Xiao, Xiang Ren, Wen-tau Yih

Figure 1 for On Continual Model Refinement in Out-of-Distribution Data Streams
Figure 2 for On Continual Model Refinement in Out-of-Distribution Data Streams
Figure 3 for On Continual Model Refinement in Out-of-Distribution Data Streams
Figure 4 for On Continual Model Refinement in Out-of-Distribution Data Streams
* Accepted to ACL 2022; Project website: https://cmr-nlp.github.io/ 
  Access Paper or Ask Questions

Unsupervised Cross-Task Generalization via Retrieval Augmentation


Apr 17, 2022
Bill Yuchen Lin, Kangmin Tan, Chris Miller, Beiwen Tian, Xiang Ren

Figure 1 for Unsupervised Cross-Task Generalization via Retrieval Augmentation
Figure 2 for Unsupervised Cross-Task Generalization via Retrieval Augmentation
Figure 3 for Unsupervised Cross-Task Generalization via Retrieval Augmentation
Figure 4 for Unsupervised Cross-Task Generalization via Retrieval Augmentation
* Project website: https://inklab.usc.edu/ReCross/ 
  Access Paper or Ask Questions

On the Robustness of Reading Comprehension Models to Entity Renaming


Oct 16, 2021
Jun Yan, Yang Xiao, Sagnik Mukherjee, Bill Yuchen Lin, Robin Jia, Xiang Ren

Figure 1 for On the Robustness of Reading Comprehension Models to Entity Renaming
Figure 2 for On the Robustness of Reading Comprehension Models to Entity Renaming
Figure 3 for On the Robustness of Reading Comprehension Models to Entity Renaming
Figure 4 for On the Robustness of Reading Comprehension Models to Entity Renaming

  Access Paper or Ask Questions

RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models


Sep 12, 2021
Bill Yuchen Lin, Wenyang Gao, Jun Yan, Ryan Moreno, Xiang Ren

Figure 1 for RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
Figure 2 for RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
Figure 3 for RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
Figure 4 for RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
* Accepted to EMNLP 2021 as a short paper. Project website: https://inklab.usc.edu/rockner/ 
  Access Paper or Ask Questions

AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction


Sep 10, 2021
Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Mahak Agarwal, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren

Figure 1 for AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction
Figure 2 for AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction
Figure 3 for AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction
Figure 4 for AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction
* 10 pages, 12 figures, Best paper at [email protected] 2021 and presented at [email protected] 2021 
  Access Paper or Ask Questions

Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning


Jun 13, 2021
Bill Yuchen Lin, Seyeon Lee, Xiaoyang Qiao, Xiang Ren

Figure 1 for Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
Figure 2 for Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
Figure 3 for Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
Figure 4 for Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
* Accepted to ACL-IJCNLP 2021 (long paper at main conference). Project website: https://inklab.usc.edu/XCSR/ 
  Access Paper or Ask Questions

Probing Causal Common Sense in Dialogue Response Generation


Apr 21, 2021
Pei Zhou, Pegah Jandaghi, Bill Yuchen Lin, Justin Cho, Jay Pujara, Xiang Ren

Figure 1 for Probing Causal Common Sense in Dialogue Response Generation
Figure 2 for Probing Causal Common Sense in Dialogue Response Generation
Figure 3 for Probing Causal Common Sense in Dialogue Response Generation
Figure 4 for Probing Causal Common Sense in Dialogue Response Generation
* This article has been withdrawn by the authors. The submitted version was an early draft that has errors in the results which renders the analysis invalid 
  Access Paper or Ask Questions

CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP


Apr 18, 2021
Qinyuan Ye, Bill Yuchen Lin, Xiang Ren

Figure 1 for CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
Figure 2 for CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
Figure 3 for CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
Figure 4 for CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP

  Access Paper or Ask Questions

FedNLP: A Research Platform for Federated Learning in Natural Language Processing


Apr 18, 2021
Bill Yuchen Lin, Chaoyang He, Zihang Zeng, Hulin Wang, Yufen Huang, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr

Figure 1 for FedNLP: A Research Platform for Federated Learning in Natural Language Processing
Figure 2 for FedNLP: A Research Platform for Federated Learning in Natural Language Processing
Figure 3 for FedNLP: A Research Platform for Federated Learning in Natural Language Processing
Figure 4 for FedNLP: A Research Platform for Federated Learning in Natural Language Processing
* Github link: https://github.com/FedML-AI/FedNLP 
  Access Paper or Ask Questions

RiddleSense: Answering Riddle Questions as Commonsense Reasoning


Jan 02, 2021
Bill Yuchen Lin, Ziyi Wu, Yichi Yang, Dong-Ho Lee, Xiang Ren

Figure 1 for RiddleSense: Answering Riddle Questions as Commonsense Reasoning
Figure 2 for RiddleSense: Answering Riddle Questions as Commonsense Reasoning
Figure 3 for RiddleSense: Answering Riddle Questions as Commonsense Reasoning
Figure 4 for RiddleSense: Answering Riddle Questions as Commonsense Reasoning
* 10 pages, 6 figures; Project page: https://inklab.usc.edu/RiddleSense 
  Access Paper or Ask Questions

Differentiable Open-Ended Commonsense Reasoning


Oct 24, 2020
Bill Yuchen Lin, Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Xiang Ren, William W. Cohen

Figure 1 for Differentiable Open-Ended Commonsense Reasoning
Figure 2 for Differentiable Open-Ended Commonsense Reasoning
Figure 3 for Differentiable Open-Ended Commonsense Reasoning
Figure 4 for Differentiable Open-Ended Commonsense Reasoning
* Work in progress. Project page: https://yuchenlin.xyz/opencsr/ 
  Access Paper or Ask Questions

FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents


Oct 21, 2020
Bill Yuchen Lin, Ying Sheng, Nguyen Vo, Sandeep Tata

Figure 1 for FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents
Figure 2 for FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents
Figure 3 for FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents
Figure 4 for FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents
* in Proc. of KDD 2020 (Research Track). Figure 5 updated 
  Access Paper or Ask Questions

IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization


May 02, 2020
Wenxuan Zhou, Bill Yuchen Lin, Xiang Ren

Figure 1 for IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization
Figure 2 for IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization
Figure 3 for IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization
Figure 4 for IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization

  Access Paper or Ask Questions

Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models


May 02, 2020
Pei Zhou, Rahul Khanna, Bill Yuchen Lin, Daniel Ho, Xiang Ren, Jay Pujara

Figure 1 for Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models
Figure 2 for Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models
Figure 3 for Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models
Figure 4 for Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models
* 15 pages, 11 figures. Work in progress 
  Access Paper or Ask Questions

Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models


May 02, 2020
Bill Yuchen Lin, Seyeon Lee, Rahul Khanna, Xiang Ren

Figure 1 for Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models
Figure 2 for Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models
Figure 3 for Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models
Figure 4 for Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models
* Project page: http://inklab.usc.edu/NumerSense/ 
  Access Paper or Ask Questions

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering


May 01, 2020
Yanlin Feng, Xinyue Chen, Bill Yuchen Lin, Peifeng Wang, Jun Yan, Xiang Ren

Figure 1 for Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
Figure 2 for Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
Figure 3 for Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
Figure 4 for Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
* 13 pages, 8 figures, Project page: https://github.com/INK-USC/MHGRN 
  Access Paper or Ask Questions

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition


Apr 24, 2020
Bill Yuchen Lin, Dong-Ho Lee, Ming Shen, Ryan Moreno, Xiao Huang, Prashant Shiralkar, Xiang Ren

Figure 1 for TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
Figure 2 for TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
Figure 3 for TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
Figure 4 for TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
* Accepted to the ACL 2020. Camera-ready version. The first two authors contributed equally. Code and data: https://github.com/INK-USC/TriggerNER 
  Access Paper or Ask Questions

LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation


Apr 16, 2020
Dong-Ho Lee, Rahul Khanna, Bill Yuchen Lin, Jamin Chen, Seyeon Lee, Qinyuan Ye, Elizabeth Boschee, Leonardo Neves, Xiang Ren

Figure 1 for LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
Figure 2 for LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
Figure 3 for LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
Figure 4 for LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
* Accepted to the ACL 2020 (demo). The first two authors contributed equally. Project page: http://inklab.usc.edu/leanlife/ 
  Access Paper or Ask Questions

CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning


Nov 09, 2019
Bill Yuchen Lin, Ming Shen, Yu Xing, Pei Zhou, Xiang Ren

Figure 1 for CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning
Figure 2 for CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning
Figure 3 for CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning
Figure 4 for CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning
* Work in process; 10 pages, Table 4 is on the last page ; The data and code can be found at http://inklab.usc.edu/CommonGen/ 
  Access Paper or Ask Questions

Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling


Oct 09, 2019
Ouyu Lan, Xiao Huang, Bill Yuchen Lin, He Jiang, Liyuan Liu, Xiang Ren

Figure 1 for Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling
Figure 2 for Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling
Figure 3 for Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling
Figure 4 for Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling
* 13 pages, 7 figures 
  Access Paper or Ask Questions

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning


Sep 04, 2019
Bill Yuchen Lin, Xinyue Chen, Jamin Chen, Xiang Ren

Figure 1 for KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
Figure 2 for KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
Figure 3 for KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
Figure 4 for KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
* 11 pages, 4 figures, in Proc. of EMNLP-IJCNLP 2019 
  Access Paper or Ask Questions

Neural Adaptation Layers for Cross-domain Named Entity Recognition


Oct 15, 2018
Bill Yuchen Lin, Wei Lu

Figure 1 for Neural Adaptation Layers for Cross-domain Named Entity Recognition
Figure 2 for Neural Adaptation Layers for Cross-domain Named Entity Recognition
Figure 3 for Neural Adaptation Layers for Cross-domain Named Entity Recognition
Figure 4 for Neural Adaptation Layers for Cross-domain Named Entity Recognition
* 11 pages, accepted as a long paper in EMNLP 2018 
  Access Paper or Ask Questions

Automatic Extraction of Commonsense LocatedNear Knowledge


May 13, 2018
Frank F. Xu, Bill Yuchen Lin, Kenny Q. Zhu

Figure 1 for Automatic Extraction of Commonsense LocatedNear Knowledge
Figure 2 for Automatic Extraction of Commonsense LocatedNear Knowledge
Figure 3 for Automatic Extraction of Commonsense LocatedNear Knowledge
Figure 4 for Automatic Extraction of Commonsense LocatedNear Knowledge
* Accepted by ACL 2018. A preliminary version is presented on [email protected]'17 
  Access Paper or Ask Questions