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 Jiawei Han

Jiawei Han

Out-of-Category Document Identification Using Target-Category Names as Weak Supervision


Nov 24, 2021
Dongha Lee, Dongmin Hyun, Jiawei Han, Hwanjo Yu

Figure 1 for Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
Figure 2 for Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
Figure 3 for Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
Figure 4 for Out-of-Category Document Identification Using Target-Category Names as Weak Supervision
* ICDM 2021. 10 pages, 4 figures 
  Access Paper or Ask Questions

MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information


Nov 07, 2021
Yu Zhang, Shweta Garg, Yu Meng, Xiusi Chen, Jiawei Han

Figure 1 for MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
Figure 2 for MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
Figure 3 for MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
Figure 4 for MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
* 9 pages; Accepted to WSDM 2022 
  Access Paper or Ask Questions

Fine-Grained Opinion Summarization with Minimal Supervision


Oct 17, 2021
Suyu Ge, Jiaxin Huang, Yu Meng, Sharon Wang, Jiawei Han

Figure 1 for Fine-Grained Opinion Summarization with Minimal Supervision
Figure 2 for Fine-Grained Opinion Summarization with Minimal Supervision
Figure 3 for Fine-Grained Opinion Summarization with Minimal Supervision
Figure 4 for Fine-Grained Opinion Summarization with Minimal Supervision

  Access Paper or Ask Questions

UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning


Oct 14, 2021
Yuning Mao, Lambert Mathias, Rui Hou, Amjad Almahairi, Hao Ma, Jiawei Han, Wen-tau Yih, Madian Khabsa

Figure 1 for UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Figure 2 for UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Figure 3 for UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Figure 4 for UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning

  Access Paper or Ask Questions

Entity Linking Meets Deep Learning: Techniques and Solutions


Sep 26, 2021
Wei Shen, Yuhan Li, Yinan Liu, Jiawei Han, Jianyong Wang, Xiaojie Yuan

Figure 1 for Entity Linking Meets Deep Learning: Techniques and Solutions
Figure 2 for Entity Linking Meets Deep Learning: Techniques and Solutions
Figure 3 for Entity Linking Meets Deep Learning: Techniques and Solutions
Figure 4 for Entity Linking Meets Deep Learning: Techniques and Solutions
* To appear in IEEE TKDE 
  Access Paper or Ask Questions

SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction


Sep 24, 2021
Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han

Figure 1 for SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction
Figure 2 for SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction
Figure 3 for SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction
Figure 4 for SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction

  Access Paper or Ask Questions

Chemical-Reaction-Aware Molecule Representation Learning


Sep 22, 2021
Hongwei Wang, Weijiang Li, Xiaomeng Jin, Kyunghyun Cho, Heng Ji, Jiawei Han, Martin D. Burke

Figure 1 for Chemical-Reaction-Aware Molecule Representation Learning
Figure 2 for Chemical-Reaction-Aware Molecule Representation Learning
Figure 3 for Chemical-Reaction-Aware Molecule Representation Learning
Figure 4 for Chemical-Reaction-Aware Molecule Representation Learning

  Access Paper or Ask Questions

Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training


Sep 10, 2021
Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, Jiawei Han

Figure 1 for Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
Figure 2 for Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
Figure 3 for Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
Figure 4 for Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
* EMNLP 2021. (Code: https://github.com/yumeng5/RoSTER) 
  Access Paper or Ask Questions

Corpus-based Open-Domain Event Type Induction


Sep 07, 2021
Jiaming Shen, Yunyi Zhang, Heng Ji, Jiawei Han

Figure 1 for Corpus-based Open-Domain Event Type Induction
Figure 2 for Corpus-based Open-Domain Event Type Induction
Figure 3 for Corpus-based Open-Domain Event Type Induction
Figure 4 for Corpus-based Open-Domain Event Type Induction
* 14 pages, EMNLP 2021 main conference 
  Access Paper or Ask Questions

Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data


Aug 02, 2021
Qi Zhu, Natalia Ponomareva, Jiawei Han, Bryan Perozzi

Figure 1 for Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data
Figure 2 for Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data
Figure 3 for Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data
Figure 4 for Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data

  Access Paper or Ask Questions

Multi-head or Single-head? An Empirical Comparison for Transformer Training


Jun 17, 2021
Liyuan Liu, Jialu Liu, Jiawei Han

Figure 1 for Multi-head or Single-head? An Empirical Comparison for Transformer Training
Figure 2 for Multi-head or Single-head? An Empirical Comparison for Transformer Training
Figure 3 for Multi-head or Single-head? An Empirical Comparison for Transformer Training
Figure 4 for Multi-head or Single-head? An Empirical Comparison for Transformer Training
* Work in progress 
  Access Paper or Ask Questions

Eider: Evidence-enhanced Document-level Relation Extraction


Jun 16, 2021
Yiqing Xie, Jiaming Shen, Sha Li, Yuning Mao, Jiawei Han

Figure 1 for Eider: Evidence-enhanced Document-level Relation Extraction
Figure 2 for Eider: Evidence-enhanced Document-level Relation Extraction
Figure 3 for Eider: Evidence-enhanced Document-level Relation Extraction
Figure 4 for Eider: Evidence-enhanced Document-level Relation Extraction

  Access Paper or Ask Questions

Training ELECTRA Augmented with Multi-word Selection


May 31, 2021
Jiaming Shen, Jialu Liu, Tianqi Liu, Cong Yu, Jiawei Han

Figure 1 for Training ELECTRA Augmented with Multi-word Selection
Figure 2 for Training ELECTRA Augmented with Multi-word Selection
Figure 3 for Training ELECTRA Augmented with Multi-word Selection
Figure 4 for Training ELECTRA Augmented with Multi-word Selection
* Accepted in Findings of ACL 2021 
  Access Paper or Ask Questions

UCPhrase: Unsupervised Context-aware Quality Phrase Tagging


May 28, 2021
Xiaotao Gu, Zihan Wang, Zhenyu Bi, Yu Meng, Liyuan Liu, Jiawei Han, Jingbo Shang

Figure 1 for UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
Figure 2 for UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
Figure 3 for UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
Figure 4 for UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
* KDD 2021 
  Access Paper or Ask Questions

Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction


Apr 15, 2021
Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss

Figure 1 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction
Figure 2 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction
Figure 3 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction
Figure 4 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction

  Access Paper or Ask Questions

Document-Level Event Argument Extraction by Conditional Generation


Apr 13, 2021
Sha Li, Heng Ji, Jiawei Han

Figure 1 for Document-Level Event Argument Extraction by Conditional Generation
Figure 2 for Document-Level Event Argument Extraction by Conditional Generation
Figure 3 for Document-Level Event Argument Extraction by Conditional Generation
Figure 4 for Document-Level Event Argument Extraction by Conditional Generation
* 11 pages. Accepted to NAACL 2021 
  Access Paper or Ask Questions

Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion


Apr 10, 2021
Xiangchen Song, Jiaming Shen, Jieyu Zhang, Jiawei Han

Figure 1 for Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
Figure 2 for Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
Figure 3 for Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
Figure 4 for Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion

  Access Paper or Ask Questions

Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks


Feb 23, 2021
Xinyang Zhang, Chenwei Zhang, Luna Xin Dong, Jingbo Shang, Jiawei Han

Figure 1 for Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
Figure 2 for Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
Figure 3 for Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
Figure 4 for Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
* WWW'21 
  Access Paper or Ask Questions

COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining


Feb 16, 2021
Yu Meng, Chenyan Xiong, Payal Bajaj, Saurabh Tiwary, Paul Bennett, Jiawei Han, Xia Song

Figure 1 for COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Figure 2 for COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Figure 3 for COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Figure 4 for COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

  Access Paper or Ask Questions

MATCH: Metadata-Aware Text Classification in A Large Hierarchy


Feb 15, 2021
Yu Zhang, Zhihong Shen, Yuxiao Dong, Kuansan Wang, Jiawei Han

Figure 1 for MATCH: Metadata-Aware Text Classification in A Large Hierarchy
Figure 2 for MATCH: Metadata-Aware Text Classification in A Large Hierarchy
Figure 3 for MATCH: Metadata-Aware Text Classification in A Large Hierarchy
Figure 4 for MATCH: Metadata-Aware Text Classification in A Large Hierarchy
* 12 pages; Accepted to WWW 2021 
  Access Paper or Ask Questions

Reader-Guided Passage Reranking for Open-Domain Question Answering


Jan 01, 2021
Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen

Figure 1 for Reader-Guided Passage Reranking for Open-Domain Question Answering
Figure 2 for Reader-Guided Passage Reranking for Open-Domain Question Answering
Figure 3 for Reader-Guided Passage Reranking for Open-Domain Question Answering
Figure 4 for Reader-Guided Passage Reranking for Open-Domain Question Answering
* TLDR: Reranking retrieved passages by reader predictions can achieve 10~20 gains in top-1 retrieval accuracy and 1~4 gains in Exact Match (EM) without any training 
  Access Paper or Ask Questions

Few-Shot Named Entity Recognition: A Comprehensive Study


Dec 29, 2020
Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han

Figure 1 for Few-Shot Named Entity Recognition: A Comprehensive Study
Figure 2 for Few-Shot Named Entity Recognition: A Comprehensive Study
Figure 3 for Few-Shot Named Entity Recognition: A Comprehensive Study
Figure 4 for Few-Shot Named Entity Recognition: A Comprehensive Study

  Access Paper or Ask Questions

Hierarchical Metadata-Aware Document Categorization under Weak Supervision


Oct 26, 2020
Yu Zhang, Xiusi Chen, Yu Meng, Jiawei Han

Figure 1 for Hierarchical Metadata-Aware Document Categorization under Weak Supervision
Figure 2 for Hierarchical Metadata-Aware Document Categorization under Weak Supervision
Figure 3 for Hierarchical Metadata-Aware Document Categorization under Weak Supervision
Figure 4 for Hierarchical Metadata-Aware Document Categorization under Weak Supervision
* 9 pages; Accepted to WSDM 2021 
  Access Paper or Ask Questions

Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation


Oct 24, 2020
Yuning Mao, Xiang Ren, Heng Ji, Jiawei Han

Figure 1 for Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
Figure 2 for Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
Figure 3 for Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
Figure 4 for Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation

  Access Paper or Ask Questions

On the Transformer Growth for Progressive BERT Training


Oct 23, 2020
Xiaotao Gu, Liyuan Liu, Hongkun Yu, Jing Li, Chen Chen, Jiawei Han

Figure 1 for On the Transformer Growth for Progressive BERT Training
Figure 2 for On the Transformer Growth for Progressive BERT Training
Figure 3 for On the Transformer Growth for Progressive BERT Training
Figure 4 for On the Transformer Growth for Progressive BERT Training

  Access Paper or Ask Questions

BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks


Oct 23, 2020
Di Jin, Xiangchen Song, Zhizhi Yu, Ziyang Liu, Heling Zhang, Zhaomeng Cheng, Jiawei Han

Figure 1 for BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
Figure 2 for BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
Figure 3 for BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
Figure 4 for BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
* To appear in WSDM 2021 
  Access Paper or Ask Questions

CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding


Oct 16, 2020
Yanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Jiawei Han, Weizhu Chen

Figure 1 for CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
Figure 2 for CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
Figure 3 for CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
Figure 4 for CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding

  Access Paper or Ask Questions

Text Classification Using Label Names Only: A Language Model Self-Training Approach


Oct 14, 2020
Yu Meng, Yunyi Zhang, Jiaxin Huang, Chenyan Xiong, Heng Ji, Chao Zhang, Jiawei Han

Figure 1 for Text Classification Using Label Names Only: A Language Model Self-Training Approach
Figure 2 for Text Classification Using Label Names Only: A Language Model Self-Training Approach
Figure 3 for Text Classification Using Label Names Only: A Language Model Self-Training Approach
Figure 4 for Text Classification Using Label Names Only: A Language Model Self-Training Approach
* EMNLP 2020. (Code: https://github.com/yumeng5/LOTClass) 
  Access Paper or Ask Questions

CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring


Oct 13, 2020
Jiaxin Huang, Yiqing Xie, Yu Meng, Yunyi Zhang, Jiawei Han

Figure 1 for CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
Figure 2 for CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
Figure 3 for CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
Figure 4 for CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
* KDD 2020 Research Track 
  Access Paper or Ask Questions