Search Results for author: Shumin Deng

Found 49 papers, 36 papers with code

Towards A Unified View of Answer Calibration for Multi-Step Reasoning

no code implementations15 Nov 2023 Shumin Deng, Ningyu Zhang, Nay Oo, Bryan Hooi

Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities.

Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

1 code implementation3 Oct 2023 Jintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu, Bryan Hooi, Shumin Deng

This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights.

Navigate

When Do Program-of-Thoughts Work for Reasoning?

1 code implementation29 Aug 2023 Zhen Bi, Ningyu Zhang, Yinuo Jiang, Shumin Deng, Guozhou Zheng, Huajun Chen

Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored.

Code Generation Mathematical Reasoning

LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities

1 code implementation22 May 2023 Yuqi Zhu, Xiaohan Wang, Jing Chen, Shuofei Qiao, Yixin Ou, Yunzhi Yao, Shumin Deng, Huajun Chen, Ningyu Zhang

We engage in experiments across eight diverse datasets, focusing on four representative tasks encompassing entity and relation extraction, event extraction, link prediction, and question-answering, thereby thoroughly exploring LLMs' performance in the domain of construction and inference.

Event Extraction graph construction +4

Editing Large Language Models: Problems, Methods, and Opportunities

3 code implementations22 May 2023 Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang

Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context.

Model Editing

Reasoning with Language Model Prompting: A Survey

2 code implementations19 Dec 2022 Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Huajun Chen

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.

Arithmetic Reasoning Common Sense Reasoning +4

Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction

1 code implementation19 Oct 2022 Yunzhi Yao, Shengyu Mao, Ningyu Zhang, Xiang Chen, Shumin Deng, Xi Chen, Huajun Chen

With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance.

Event Extraction graph construction +2

Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

2 code implementations29 May 2022 Xiang Chen, Lei LI, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.

Few-Shot Text Classification Memorization +5

Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction

1 code implementation7 May 2022 Xiang Chen, Ningyu Zhang, Lei LI, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

To deal with these issues, we propose a novel Hierarchical Visual Prefix fusion NeTwork (HVPNeT) for visual-enhanced entity and relation extraction, aiming to achieve more effective and robust performance.

named-entity-recognition Named Entity Recognition +3

Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

1 code implementation4 May 2022 Xiang Chen, Ningyu Zhang, Lei LI, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen

Since most MKGs are far from complete, extensive knowledge graph completion studies have been proposed focusing on the multimodal entity, relation extraction and link prediction.

Information Retrieval Link Prediction +4

Information Extraction in Low-Resource Scenarios: Survey and Perspective

2 code implementations16 Feb 2022 Shumin Deng, Yubo Ma, Ningyu Zhang, Yixin Cao, Bryan Hooi

Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes.

Ontology-enhanced Prompt-tuning for Few-shot Learning

no code implementations27 Jan 2022 Hongbin Ye, Ningyu Zhang, Shumin Deng, Xiang Chen, Hui Chen, Feiyu Xiong, Xi Chen, Huajun Chen

Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text.

Event Extraction Few-Shot Learning +1

OntoProtein: Protein Pretraining With Gene Ontology Embedding

1 code implementation ICLR 2022 Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Jiazhang Lian, Qiang Zhang, Huajun Chen

We construct a novel large-scale knowledge graph that consists of GO and its related proteins, and gene annotation texts or protein sequences describe all nodes in the graph.

Contrastive Learning Knowledge Graphs +2

Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules

no code implementations16 Dec 2021 Wen Zhang, Shumin Deng, Mingyang Chen, Liang Wang, Qiang Chen, Feiyu Xiong, Xiangwen Liu, Huajun Chen

We first identity three important desiderata for e-commerce KG systems: 1) attentive reasoning, reasoning over a few target relations of more concerns instead of all; 2) explanation, providing explanations for a prediction to help both users and business operators understand why the prediction is made; 3) transferable rules, generating reusable rules to accelerate the deployment of a KG to new systems.

Entity Embeddings Graph Attention +4

Molecular Contrastive Learning with Chemical Element Knowledge Graph

1 code implementation1 Dec 2021 Yin Fang, Qiang Zhang, Haihong Yang, Xiang Zhuang, Shumin Deng, Wen Zhang, Ming Qin, Zhuo Chen, Xiaohui Fan, Huajun Chen

To address these issues, we construct a Chemical Element Knowledge Graph (KG) to summarize microscopic associations between elements and propose a novel Knowledge-enhanced Contrastive Learning (KCL) framework for molecular representation learning.

Contrastive Learning Molecular Property Prediction +3

Learning to Ask for Data-Efficient Event Argument Extraction

no code implementations1 Oct 2021 Hongbin Ye, Ningyu Zhang, Zhen Bi, Shumin Deng, Chuanqi Tan, Hui Chen, Fei Huang, Huajun Chen

Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles.

Event Argument Extraction

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

4 code implementations ICLR 2022 Ningyu Zhang, Luoqiu Li, Xiang Chen, Shumin Deng, Zhen Bi, Chuanqi Tan, Fei Huang, Huajun Chen

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners.

Language Modelling Prompt Engineering

Document-level Relation Extraction as Semantic Segmentation

2 code implementations7 Jun 2021 Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Luo Si, Huajun Chen

Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples.

Document-level Relation Extraction Relation +2

KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction

1 code implementation15 Apr 2021 Xiang Chen, Ningyu Zhang, Xin Xie, Shumin Deng, Yunzhi Yao, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

To this end, we focus on incorporating knowledge among relation labels into prompt-tuning for relation extraction and propose a Knowledge-aware Prompt-tuning approach with synergistic optimization (KnowPrompt).

Ranked #5 on Dialog Relation Extraction on DialogRE (F1 (v1) metric)

Dialog Relation Extraction Language Modelling +3

Disentangled Contrastive Learning for Learning Robust Textual Representations

1 code implementation11 Apr 2021 Xiang Chen, Xin Xie, Zhen Bi, Hongbin Ye, Shumin Deng, Ningyu Zhang, Huajun Chen

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.

Contrastive Learning

Text-guided Legal Knowledge Graph Reasoning

1 code implementation6 Apr 2021 Luoqiu Li, Zhen Bi, Hongbin Ye, Shumin Deng, Hui Chen, Huaixiao Tou

In this paper, we propose a novel legal application of legal provision prediction (LPP), which aims to predict the related legal provisions of affairs.

Knowledge Graph Completion

Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction

1 code implementation1 Apr 2021 Luoqiu Li, Xiang Chen, Zhen Bi, Xin Xie, Shumin Deng, Ningyu Zhang, Chuanqi Tan, Mosha Chen, Huajun Chen

Recent neural-based relation extraction approaches, though achieving promising improvement on benchmark datasets, have reported their vulnerability towards adversarial attacks.

Relation Relation Extraction

Towards Robust Textual Representations with Disentangled Contrastive Learning

no code implementations1 Jan 2021 Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Yantao Jia, Zonggang Yuan, Huajun Chen

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.

Contrastive Learning

Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction

no code implementations COLING 2020 Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei zhang, Huajun Chen

Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings.

The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis

1 code implementation15 Sep 2020 Haiyang Yu, Ningyu Zhang, Shumin Deng, Zonggang Yuan, Yantao Jia, Huajun Chen

Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance.

General Classification Relation +1

On Robustness and Bias Analysis of BERT-based Relation Extraction

1 code implementation14 Sep 2020 Luoqiu Li, Xiang Chen, Hongbin Ye, Zhen Bi, Shumin Deng, Ningyu Zhang, Huajun Chen

Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks.

counterfactual Relation +1

Relation Adversarial Network for Low Resource Knowledge Graph Completion

no code implementations8 Nov 2019 Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoayan Chen, Wei zhang, Huajun Chen

Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations.

Link Prediction Partial Domain Adaptation +2

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

1 code implementation25 Oct 2019 Shumin Deng, Ningyu Zhang, Jiaojian Kang, Yichi Zhang, Wei zhang, Huajun Chen

Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs.

Event Detection Event Extraction +2

Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning

no code implementations22 Aug 2019 Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoyan Chen, Wei zhang, Huajun Chen

However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision samples are usually noisy.

Partial Domain Adaptation Relation +2

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

no code implementations NAACL 2019 Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei zhang, Huajun Chen

Here, the challenge is to learn accurate "few-shot" models for classes existing at the tail of the class distribution, for which little data is available.

Knowledge Graph Embeddings Relation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.