370 citations · 1.4k across the 49 of their papers we have counts for
14 papers · 1 filter
SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformers
Hongyi Yuan, Zheng Yuan, Chuanqi Tan +2
Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text…
Reasoning with Language Model Prompting: A Survey
Shuofei Qiao, Yixin Ou, Ningyu Zhang +6
Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This…
HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation
Hongyi Yuan, Zheng Yuan, Chuanqi Tan +2
Language models with the Transformers structure have shown great performance in natural language processing. However, there still poses problems when fine-tuning pre-trained langua…
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
Jianing Wang, Chengcheng Han, Chengyu Wang +5
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, whi…
Parameter-Efficient Sparsity for Large Language Models Fine-Tuning
Yuchao Li, Fuli Luo, Chuanqi Tan +4
With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While…
Towards Unified Prompt Tuning for Few-shot Text Classification
Jianing Wang, Chengyu Wang, Fuli Luo +6
Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamil…
Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
Xiang Chen, Ningyu Zhang, Lei Li +6
Multimodal named entity recognition and relation extraction (MNER and MRE) is a fundamental and crucial branch in information extraction. However, existing approaches for MNER and…
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
Xiang Chen, Lei Li, Ningyu Zhang +6
Prompt learning approaches have made waves in natural language processing by inducing better few-shot performance while they still follow a parametric-based learning paradigm; the…
Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
Xiang Chen, Ningyu Zhang, Lei Li +6
Multimodal Knowledge Graphs (MKGs), which organize visual-text factual knowledge, have recently been successfully applied to tasks such as information retrieval, question answering…
Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning
Xiang Chen, Lei Li, Ningyu Zhang +4
Pre-trained language models have contributed significantly to relation extraction by demonstrating remarkable few-shot learning abilities. However, prompt tuning methods for relati…
Contrastive Demonstration Tuning for Pre-trained Language Models
Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng +3
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios. Recent works have focused on automatically searchin…
Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding
Zheng Yuan, Chuanqi Tan, Songfang Huang
Automatic ICD coding is defined as assigning disease codes to electronic medical records (EMRs). Existing methods usually apply label attention with code representations to match r…
Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings
Peng Wang, Xin Xie, Xiaohan Wang +1
Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they typically struggle to rea…
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
Ningyu Zhang, Xin Xu, Liankuan Tao +19
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base pop…