ReactIE: Enhancing Chemical Reaction Extraction with Weak Supervision
Comments Findings of ACL 2023, Short Paper
作者
Jiawei Han
Data Mining
Explaining and Adapting Graph Conditional Shift
Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks
Comments KDD 2023. (Code: https://github.com/PeterGriffinJin/Heterformer)
Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models
Comments 18 pages, 11 figures, 8 tables. Accepted by ACL 23' Findings
Patton: Language Model Pretraining on Text-Rich Networks
Comments ACL 2023. (Code: https://github.com/PeterGriffinJin/Patton)
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning
Comments ICML 2023. (Code: https://github.com/yumeng5/FewGen)
Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding
Comments Accepted by SIGIR'23
Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks
Comments ICLR 2023. (Code: https://github.com/PeterGriffinJin/Edgeformers)
PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream
Comments Accepted by WWW'23
Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories
Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts
Comments 9 pages; Accepted to WSDM 2023
P4E: Few-Shot Event Detection as Prompt-Guided Identification and Localization
Comments 13 pages, fixed typos and additional experiments
Unsupervised Multi-Granularity Summarization
Comments EMNLP 2022 Findings
Entity Set Co-Expansion in StackOverflow
Comments 4 pages; Accepted to IEEE BigData 2022
Open Relation and Event Type Discovery with Type Abstraction
Comments Accepted to EMNLP 2022. 14 pages
Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation
Comments 14 pages, 7 figures, Findings of EMNLP 2022 (Long paper)
Open-Vocabulary Argument Role Prediction for Event Extraction
Comments EMNLP 2022 Findings
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
Comments Findings of EMNLP 2022
Large Language Models Can Self-Improve
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
Comments EMNLP 2022. TLDR: By pretraining on (automatically extracted) citation sentences in scientific papers, we achieve SOTA on SciTLDR, XSum, and Gigaword in zero-shot and (or) few-shot settings
Towards a Unified Multi-Dimensional Evaluator for Text Generation
Comments EMNLP 2022
Generating Training Data with Language Models: Towards Zero-Shot Language Understanding
Comments NeurIPS 2022. (Code: https://github.com/yumeng5/SuperGen)
Few-shot Text Classification with Dual Contrastive Consistency
Comments 8 pages, 2 figures, under review
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Comments ACL 2022 (w. typo fixes)
MentorGNN: Deriving Curriculum for Pre-Training GNNs
Comments Accepted by CIKM 2022
Unsupervised Key Event Detection from Massive Text Corpora
Comments Accepted to KDD 2022 Research Track
Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation
Comments Accepted to KDD 2022 Research Track
