b'Jiawei Han'

research

∙ 05/24/2023

Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models

The mission of open knowledge graph (KG) completion is to draw new findi...

0 Pengcheng Jiang, et al. ∙

research

∙ 05/23/2023

Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation

Instruction tuning has emerged to enhance the capabilities of large lang...

0 Da Yin, et al. ∙

research

∙ 05/21/2023

OntoType: Ontology-Guided Zero-Shot Fine-Grained Entity Typing with Weak Supervision from Pre-Trained Language Models

Fine-grained entity typing (FET), which assigns entities in text with co...

0 Tanay Komarlu, et al. ∙

research

∙ 05/20/2023

Patton: Language Model Pretraining on Text-Rich Networks

A real-world text corpus sometimes comprises not only text documents but...

0 Bowen Jin, et al. ∙

research

∙ 04/08/2023

Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding

Unsupervised discovery of stories with correlated news articles in real-...

0 Susik Yoon, et al. ∙

research

∙ 04/04/2023

MEGClass: Text Classification with Extremely Weak Supervision via Mutually-Enhancing Text Granularities

Text classification typically requires a substantial amount of human-ann...

0 Priyanka Kargupta, et al. ∙

research

∙ 03/16/2023

GLEN: General-Purpose Event Detection for Thousands of Types

The development of event extraction systems has been hindered by the abs...

0 Qiusi Zhan, et al. ∙

research

∙ 02/21/2023

Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks

Edges in many real-world social/information networks are associated with...

0 Bowen Jin, et al. ∙

research

∙ 02/10/2023

PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream

Summarizing text-rich documents has been long studied in the literature,...

0 Susik Yoon, et al. ∙

research

∙ 02/07/2023

Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories

In this paper we improve the zero-shot generalization ability of languag...

0 Suyu Ge, et al. ∙

research

∙ 02/07/2023

The Effect of Metadata on Scientific Literature Tagging: A Cross-Field Cross-Model Study

Due to the exponential growth of scientific publications on the Web, the...

0 Yu Zhang, et al. ∙

research

∙ 02/04/2023

Representation Deficiency in Masked Language Modeling

Masked Language Modeling (MLM) has been one of the most prominent approa...

0 Yu Meng, et al. ∙

research

∙ 12/12/2022

Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts

Instead of mining coherent topics from a given text corpus in a complete...

0 Yu Zhang, et al. ∙

research

∙ 12/05/2022

Entity Set Co-Expansion in StackOverflow

Given a few seed entities of a certain type (e.g., Software or Programmi...

0 Yu Zhang, et al. ∙

research

∙ 11/30/2022

Open Relation and Event Type Discovery with Type Abstraction

Conventional closed-world information extraction (IE) approaches rely on...

0 Sha Li, et al. ∙

research

∙ 11/06/2022

Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning

Recent studies have revealed the intriguing few-shot learning ability of...

0 Yu Meng, et al. ∙

research

∙ 11/03/2022

Open-Vocabulary Argument Role Prediction for Event Extraction

The argument role in event extraction refers to the relation between an ...

0 Yizhu Jiao, et al. ∙

research

∙ 10/20/2022

Large Language Models Can Self-Improve

Large Language Models (LLMs) have achieved excellent performances in var...

1 Jiaxin Huang, et al. ∙

research

∙ 09/29/2022

Few-shot Text Classification with Dual Contrastive Consistency

In this paper, we explore how to utilize pre-trained language model to p...

0 Liwen Sun, et al. ∙

research

∙ 09/15/2022

TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations

We present TwHIN-BERT, a multilingual language model trained on in-domai...

0 Xinyang Zhang, et al. ∙

research

∙ 08/21/2022

MentorGNN: Deriving Curriculum for Pre-Training GNNs

Graph pre-training strategies have been attracting a surge of attention ...

13 Dawei Zhou, et al. ∙

research

∙ 06/28/2022

Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation

We study the problem of few-shot Fine-grained Entity Typing (FET), where...

0 Jiaxin Huang, et al. ∙

research

∙ 06/15/2022

TeKo: Text-Rich Graph Neural Networks with External Knowledge

Graph Neural Networks (GNNs) have gained great popularity in tackling va...

1 Zhizhi Yu, et al. ∙

research

∙ 06/06/2022

Schema-Guided Event Graph Completion

We tackle a new task, event graph completion, which aims to predict miss...

0 Hongwei Wang, et al. ∙

research

∙ 05/22/2022

All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass

Multi-Task Learning (MTL) models have shown their robustness, effectiven...

0 Jiaxin Huang, et al. ∙

research

∙ 05/20/2022

Heterformer: A Transformer Architecture for Node Representation Learning on Heterogeneous Text-Rich Networks

We study node representation learning on heterogeneous text-rich network...

0 Bowen Jin, et al. ∙

research

∙ 05/12/2022

CiteSum: Citation Text-guided Scientific Extreme Summarization and Low-resource Domain Adaptation

Scientific extreme summarization (TLDR) aims to form ultra-short summari...

0 Yuning Mao, et al. ∙

research

∙ 05/04/2022

Seed-Guided Topic Discovery with Out-of-Vocabulary Seeds

Discovering latent topics from text corpora has been studied for decades...

0 Yu Zhang, et al. ∙

research

∙ 04/29/2022

OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision

Automatic extraction of product attributes from their textual descriptio...

9 Xinyang Zhang, et al. ∙

research

∙ 04/07/2022

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

We present a new framework AMOS that pretrains text encoders with an Adv...

0 Yu Meng, et al. ∙

research

∙ 02/15/2022

PILED: An Identify-and-Localize Framework for Few-Shot Event Detection

Practical applications of event extraction systems have long been hinder...

0 Sha Li, et al. ∙

research

∙ 02/11/2022

Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification

Large-scale multi-label text classification (LMTC) aims to associate a d...

0 Yu Zhang, et al. ∙

research

∙ 02/10/2022

TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations

Taxonomies are fundamental to many real-world applications in various do...

0 Minhao Jiang, et al. ∙

research

∙ 02/09/2022

Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations

Topic models have been the prominent tools for automatic topic discovery...

0 Yu Meng, et al. ∙

research

∙ 02/09/2022

Generating Training Data with Language Models: Towards Zero-Shot Language Understanding

Pretrained language models (PLMs) have demonstrated remarkable performan...

0 Yu Meng, et al. ∙

research

∙ 11/24/2021

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

Identifying outlier documents, whose content is different from the major...

0 Dongha Lee, et al. ∙

research

∙ 11/07/2021

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

We study the problem of weakly supervised text classification, which aim...

0 Yu Zhang, et al. ∙

research

∙ 10/17/2021

Fine-Grained Opinion Summarization with Minimal Supervision

Opinion summarization aims to profile a target by extracting opinions fr...

0 Suyu Ge, et al. ∙

research

∙ 10/14/2021

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

Conventional fine-tuning of pre-trained language models tunes all model ...

1 Yuning Mao, et al. ∙

research

∙ 09/26/2021

Entity Linking Meets Deep Learning: Techniques and Solutions

Entity linking (EL) is the process of linking entity mentions appearing ...

25 Wei Shen, et al. ∙

research

∙ 09/21/2021

Chemical-Reaction-Aware Molecule Representation Learning

Molecule representation learning (MRL) methods aim to embed molecules in...

16 Hongwei Wang, et al. ∙

research

∙ 09/10/2021

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

We study the problem of training named entity recognition (NER) models u...

0 Yu Meng, et al. ∙

research

∙ 08/02/2021

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

There has been a recent surge of interest in designing Graph Neural Netw...

0 Qi Zhu, et al. ∙

research

∙ 06/17/2021

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

Multi-head attention plays a crucial role in the recent success of Trans...

0 Liyuan Liu, et al. ∙

research

∙ 05/28/2021

UCPhrase: Unsupervised Context-aware Quality Phrase Tagging

Identifying and understanding quality phrases from context is a fundamen...

0 Xiaotao Gu, et al. ∙

research

∙ 04/13/2021

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

Event schemas encode knowledge of stereotypical structures of events and...

8 Manling Li, et al. ∙

research

∙ 04/13/2021

Document-Level Event Argument Extraction by Conditional Generation

Event extraction has long been treated as a sentence-level task in the I...

0 Sha Li, et al. ∙

research

∙ 02/23/2021

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

Text categorization is an essential task in Web content analysis. Consid...

0 Xinyang Zhang, et al. ∙

research

∙ 02/16/2021

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

We present COCO-LM, a new self-supervised learning framework that pretra...

0 Yu Meng, et al. ∙

research

∙ 02/15/2021

MATCH: Metadata-Aware Text Classification in A Large Hierarchy

Multi-label text classification refers to the problem of assigning each ...

0 Yu Zhang, et al. ∙

Jiawei Han

Featured Co-authors