1 code implementation • Findings (NAACL) 2022 • Xiang Chen, Ningyu Zhang, Lei LI, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen
Multimodal named entity recognition and relation extraction (MNER and MRE) is a fundamental and crucial branch in information extraction.
1 code implementation • 26 Jan 2023 • Yin Fang, Ningyu Zhang, Zhuo Chen, Xiaohui Fan, Huajun Chen
We further propose multi-task molecular prefix tuning across several molecular generation tasks and different molecular domains (synthetic & natural products) with a self-feedback mechanism.
2 code implementations • 25 Jan 2023 • Siyuan Cheng, Ningyu Zhang, Bozhong Tian, Zelin Dai, Feiyu Xiong, Wei Guo, Huajun Chen
We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task.
2 code implementations • 25 Jan 2023 • Xiang Chen, Lei LI, Shuofei Qiao, Ningyu Zhang, Chuanqi Tan, Yong Jiang, Fei Huang, Huajun Chen
Previous typical solutions mainly obtain a NER model by pre-trained language models (PLMs) with data from a rich-resource domain and adapt it to the target domain.
no code implementations • 2 Jan 2023 • Yacheng He, Qianghuai Jia, Lin Yuan, Ruopeng Li, Yixin Ou, Ningyu Zhang
This paper illustrates the technologies of user next intent prediction with a concept knowledge graph.
2 code implementations • 19 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.
2 code implementations • 14 Nov 2022 • Lei LI, Xiang Chen, Shuofei Qiao, Feiyu Xiong, Huajun Chen, Ningyu Zhang
Multimodal relation extraction is an essential task for knowledge graph construction.
1 code implementation • 23 Oct 2022 • Hongbin Ye, Ningyu Zhang, Hui Chen, Huajun Chen
Our contributions are threefold: (1) We present a detailed, complete taxonomy for the generative KGC methods; (2) We provide a theoretical and empirical analysis of the generative KGC methods; (3) We propose several research directions that can be developed in the future.
2 code implementations • 19 Oct 2022 • Xin Xu, Xiang Chen, Ningyu Zhang, Xin Xie, Xi Chen, Huajun Chen
This paper presents an empirical study to build relation extraction systems in low-resource settings.
1 code implementation • 19 Oct 2022 • Yunzhi Yao, Shengyu Mao, Xiang Chen, Ningyu Zhang, Shumin Deng, Huajun Chen
In this paper, we propose a novel approach of schema-aware Reference As Prompt (RAP), which dynamically leverage schema and knowledge inherited from global (few-shot) training data for each sample.
1 code implementation • 1 Oct 2022 • Ningyu Zhang, Lei LI, Xiang Chen, Xiaozhuan Liang, Shumin Deng, Huajun Chen
Analogical reasoning is fundamental to human cognition and holds an important place in various fields.
2 code implementations • 1 Oct 2022 • Xin Xie, Zhoubo Li, Xiaohan Wang, Shumin Deng, Feiyu Xiong, Huajun Chen, Ningyu Zhang
Knowledge Graphs (KGs) often have two characteristics: heterogeneous graph structure and text-rich entity/relation information.
1 code implementation • 30 Sep 2022 • Shumin Deng, Chengming Wang, Zhoubo Li, Ningyu Zhang, Zelin Dai, Hehong Chen, Feiyu Xiong, Ming Yan, Qiang Chen, Mosha Chen, Jiaoyan Chen, Jeff Z. Pan, Bryan Hooi, Huajun Chen
We release all the open resources (OpenBG benchmarks) derived from it for the community and report experimental results of KG-centric tasks.
1 code implementation • 7 Sep 2022 • Ruijie Hou, Yanran Li, Ningyu Zhang, Yulin Zhou, Xiaosong Yang, Zhao Wang
Our module can work seamlessly with the existing action classification model.
1 code implementation • 26 Jul 2022 • Zhuo Chen, Yufeng Huang, Jiaoyan Chen, Yuxia Geng, Yin Fang, Jeff Pan, Ningyu Zhang, Wen Zhang
Visual question answering (VQA) often requires an understanding of visual concepts and language semantics, which relies on external knowledge.
2 code implementations • 29 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.
no code implementations • 27 May 2022 • Siyuan Cheng, Xiaozhuan Liang, Zhen Bi, Huajun Chen, Ningyu Zhang
Existing data-centric methods for protein science generally cannot sufficiently capture and leverage biology knowledge, which may be crucial for many protein tasks.
1 code implementation • 22 May 2022 • Yincen Qu, Ningyu Zhang, Hui Chen, Zelin Dai, Zezhong Xu, Chengming Wang, Xiaoyu Wang, Qiang Chen, Huajun Chen
In addition to formulating the new task, we also release a new Benchmark dataset of Salience Evaluation in E-commerce (BSEE) and hope to promote related research on commonsense knowledge salience evaluation.
1 code implementation • 22 May 2022 • Zhen Bi, Siyuan Cheng, Jing Chen, Xiaozhuan Liang, Ningyu Zhang, Feiyu Xiong, Huajun Chen
To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer.
Ranked #1 on
Link Prediction
on FB15k-237
1 code implementation • 7 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.
1 code implementation • 4 May 2022 • Xiang Chen, Lei LI, Ningyu Zhang, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen
Note that the previous parametric learning paradigm can be viewed as memorization regarding training data as a book and inference as the close-book test.
1 code implementation • 4 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.
1 code implementation • 9 Apr 2022 • Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng, Zhenru Zhang, Chuanqi Tan, Huajun Chen
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios.
1 code implementation • 25 Feb 2022 • Wen Zhang, Xiangnan Chen, Zhen Yao, Mingyang Chen, Yushan Zhu, Hongtao Yu, Yufeng Huang, Zezhong Xu, Yajing Xu, Ningyu Zhang, Zonggang Yuan, Feiyu Xiong, Huajun Chen
NeuralKG is an open-source Python-based library for diverse representation learning of knowledge graphs.
2 code implementations • 16 Feb 2022 • Shumin Deng, Ningyu Zhang, Feiyu Xiong, Jeff Z. Pan, Huajun Chen
Knowledge Extraction (KE), aiming to extract structural information from unstructured texts, often suffers from data scarcity and emerging unseen types, i. e., low-resource scenarios.
1 code implementation • 4 Feb 2022 • Xin Xie, Ningyu Zhang, Zhoubo Li, Shumin Deng, Hui Chen, Feiyu Xiong, Mosha Chen, Huajun Chen
Knowledge graph completion aims to address the problem of extending a KG with missing triples.
Ranked #43 on
Link Prediction
on FB15k-237
no code implementations • 27 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.
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.
1 code implementation • 15 Jan 2022 • Yunzhi Yao, Shaohan Huang, Li Dong, Furu Wei, Huajun Chen, Ningyu Zhang
In this work, we propose a simple model, Kformer, which takes advantage of the knowledge stored in PTMs and external knowledge via knowledge injection in Transformer FFN layers.
1 code implementation • 14 Jan 2022 • Ningyu Zhang, Xin Xie, Xiang Chen, Xu Cheng, Huajun Chen
Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they struggle to reason rare or emerging unseen entities.
Ranked #1 on
Link Prediction
on FB15k-237-ind
1 code implementation • 10 Jan 2022 • Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Shuofei Qiao, Xin Xie, Xiang Chen, Zhoubo Li, Lei LI, Xiaozhuan Liang, Yunzhi Yao, Shumin Deng, Peng Wang, Wen Zhang, Zhenru Zhang, Chuanqi Tan, Qiang Chen, Feiyu Xiong, Fei Huang, Guozhou Zheng, Huajun Chen
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
Attribute Extraction
Cross-Domain Named Entity Recognition
+3
no code implementations • 2 Dec 2021 • Shumin Deng, Ningyu Zhang, Jiacheng Yang, Hongbin Ye, Chuanqi Tan, Mosha Chen, Songfang Huang, Fei Huang, Huajun Chen
Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation.
no code implementations • 1 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.
no code implementations • 17 Sep 2021 • Chengxi Li, Feiyu Gao, Jiajun Bu, Lu Xu, Xiang Chen, Yu Gu, Zirui Shao, Qi Zheng, Ningyu Zhang, Yongpan Wang, Zhi Yu
We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets.
1 code implementation • COLING 2022 • Xiang Chen, Lei LI, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen, Ningyu Zhang
Most NER methods rely on extensive labeled data for model training, which struggles in the low-resource scenarios with limited training data.
2 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.
Ranked #1 on
Few-Shot Learning
on SST-2 Binary classification
1 code implementation • 20 Aug 2021 • Yushan Zhu, Huaixiao Tou, Wen Zhang, Ganqiang Ye, Hui Chen, Ningyu Zhang, Huajun Chen
In this paper, we address multi-modal pretraining of product data in the field of E-commerce.
1 code implementation • ACL 2021 • Hengyi Zheng, Rui Wen, Xi Chen, Yifan Yang, Yunyan Zhang, Ziheng Zhang, Ningyu Zhang, Bin Qin, Ming Xu, Yefeng Zheng
Joint extraction of entities and relations from unstructured texts is a crucial task in information extraction.
1 code implementation • ACL 2022 • Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei LI, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice.
Ranked #1 on
Medical Relation Extraction
on CMeIE
2 code implementations • 7 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.
Ranked #3 on
Relation Extraction
on ReDocRED
1 code implementation • 3 Jun 2021 • Ningyu Zhang, Qianghuai Jia, Shumin Deng, Xiang Chen, Hongbin Ye, Hui Chen, Huaixiao Tou, Gang Huang, Zhao Wang, Nengwei Hua, Huajun Chen
Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search.
no code implementations • NAACL 2021 • Junjie Luo, Xi Chen, Jichao Sun, Yuejia Xiang, Ningyu Zhang, Xiang Wan
Word representations empowered with additional linguistic information have been widely studied and proved to outperform traditional embeddings.
1 code implementation • ACL 2021 • Shumin Deng, Ningyu Zhang, Luoqiu Li, Hui Chen, Huaixiao Tou, Mosha Chen, Fei Huang, Huajun Chen
Most of current methods to ED rely heavily on training instances, and almost ignore the correlation of event types.
1 code implementation • ACL 2021 • Dongfang Lou, Zhilin Liao, Shumin Deng, Ningyu Zhang, Huajun Chen
We consider the problem of collectively detecting multiple events, particularly in cross-sentence settings.
1 code implementation • 12 May 2021 • Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yuejia Xiang, Ningyu Zhang, Yefeng Zheng
Knowledge Graph (KG) alignment is to discover the mappings (i. e., equivalent entities, relations, and others) between two KGs.
no code implementations • 20 Apr 2021 • Zhen Bi, Ningyu Zhang, Ganqiang Ye, Haiyang Yu, Xi Chen, Huajun Chen
Recent neural-based aspect-based sentiment analysis approaches, though achieving promising improvement on benchmark datasets, have reported suffering from poor robustness when encountering confounder such as non-target aspects.
1 code implementation • 15 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)
1 code implementation • 11 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.
1 code implementation • NAACL 2021 • Kun Liu, Yao Fu, Chuanqi Tan, Mosha Chen, Ningyu Zhang, Songfang Huang, Sheng Gao
This work studies NER under a noisy labeled setting with calibrated confidence estimation.
1 code implementation • 1 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.
1 code implementation • SEMEVAL 2021 • Xin Xie, Xiangnan Chen, Xiang Chen, Yong Wang, Ningyu Zhang, Shumin Deng, Huajun Chen
This paper presents our systems for the three Subtasks of SemEval Task4: Reading Comprehension of Abstract Meaning (ReCAM).
Ranked #1 on
Reading Comprehension
on ReCAM
(using extra training data)
no code implementations • 1 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.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Ningyu Zhang, Shumin Deng, Juan Li, Xi Chen, Wei zhang, Huajun Chen
It is desirable to generate answer summaries for online search engines, particularly summaries that can reveal direct answers to questions.
no code implementations • COLING 2020 • Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, Huajun Chen
To recognize unseen relations at test time, we explore the problem of zero-shot relation classification.
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.
1 code implementation • EMNLP 2020 • Ningyu Zhang, Shumin Deng, Zhen Bi, Haiyang Yu, Jiacheng Yang, Mosha Chen, Fei Huang, Wei zhang, Huajun Chen
We introduce a prototype model and provide an open-source and extensible toolkit called OpenUE for various extraction tasks.
no code implementations • COLING 2022 • Zifeng Wang, Rui Wen, Xi Chen, Shao-Lun Huang, Ningyu Zhang, Yefeng Zheng
Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise.
1 code implementation • 15 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.
1 code implementation • 14 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.
no code implementations • 14 Sep 2020 • Hongbin Ye, Ningyu Zhang, Shumin Deng, Mosha Chen, Chuanqi Tan, Fei Huang, Huajun Chen
In this paper, we revisit the end-to-end triple extraction task for sequence generation.
Ranked #8 on
Relation Extraction
on WebNLG
1 code implementation • 25 Aug 2020 • Ningyu Zhang, Qianghuai Jia, Kangping Yin, Liang Dong, Feng Gao, Nengwei Hua
In this paper, we investigate how the recently introduced pre-trained language model BERT can be adapted for Chinese biomedical corpora and propose a novel conceptualized representation learning approach.
no code implementations • 8 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.
1 code implementation • 25 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.
no code implementations • 6 Sep 2019 • Qianghuai Jia, Ningyu Zhang, Nengwei Hua
Entity recommendation, providing search users with an improved experience via assisting them in finding related entities for a given query, has become an indispensable feature of today's search engines.
no code implementations • 22 Aug 2019 • Shumin Deng, Ningyu Zhang, Zhanlin Sun, Jiaoyan Chen, Huajun Chen
Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes.
Ranked #1 on
Multi-Domain Sentiment Classification
on ARSC
no code implementations • 22 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.
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.
1 code implementation • EMNLP 2018 • Ningyu Zhang, Shumin Deng, Zhanlin Sun, Xi Chen, Wei zhang, Huajun Chen
A capsule is a group of neurons, whose activity vector represents the instantiation parameters of a specific type of entity.