Search Results for author: Zhen Tan

Found 7 papers, 2 papers with code

Relation-aware Bidirectional Path Reasoning for Commonsense Question Answering

no code implementations CoNLL (EMNLP) 2021 Junxing Wang, Xinyi Li, Zhen Tan, Xiang Zhao, Weidong Xiao

A bidirectional attention mechanism is applied between the question sequence and the paths that connect entities, which provides us with transparent interpretability.

Knowledge Graphs Question Answering

A Simple Yet Effective Pretraining Strategy for Graph Few-shot Learning

no code implementations29 Mar 2022 Zhen Tan, Kaize Ding, Ruocheng Guo, Huan Liu

Recently, increasing attention has been devoted to the graph few-shot learning problem, where the target novel classes only contain a few labeled nodes.

Contrastive Learning Data Augmentation +2

Graph Few-shot Class-incremental Learning

1 code implementation23 Dec 2021 Zhen Tan, Kaize Ding, Ruocheng Guo, Huan Liu

The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems.

class-incremental learning Incremental Learning +2

Joint Event Extraction with Hierarchical Policy Network

no code implementations COLING 2020 Peixin Huang, Xiang Zhao, Ryuichi Takanobu, Zhen Tan, Weidong Xiao

Most existing work on event extraction (EE) either follows a pipelined manner or uses a joint structure but is pipelined in essence.

Event Detection Event Extraction

Degree-Aware Alignment for Entities in Tail

1 code implementation25 May 2020 Weixin Zeng, Xiang Zhao, Wei Wang, Jiuyang Tang, Zhen Tan

Entity alignment (EA) is to discover equivalent entities in knowledge graphs (KGs), which bridges heterogeneous sources of information and facilitates the integration of knowledge.

Entity Alignment Knowledge Graphs +1

CLEEK: A Chinese Long-text Corpus for Entity Linking

no code implementations LREC 2020 Weixin Zeng, Xiang Zhao, Jiuyang Tang, Zhen Tan, Xuqian Huang

Moreover, we devise a measure to evaluate the difficulty of documents with respect to entity linking, which is then used to characterize the corpus.

Entity Linking

Jointly Extracting Multiple Triplets with Multilayer Translation Constraints

no code implementations AAAI-2019 2019 Zhen Tan, Xiang Zhao, Wei Wang, Weidong Xiao

Triplets extraction is an essential and pivotal step in automatic knowledge base construction, which captures structural information from unstructured text corpus.

Named Entity Recognition Relation Classification +1

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