Joint Type Inference on Entities and Relations via Graph Convolutional Networks

  title={Joint Type Inference on Entities and Relations via Graph Convolutional Networks},
  author={Changzhi Sun and Yeyun Gong and Yuanbin Wu and Ming Gong and Daxin Jiang and Man Lan and Shiliang Sun and Nan Duan},
  booktitle={Annual Meeting of the Association for Computational Linguistics},
We develop a new paradigm for the task of joint entity relation extraction. [] Key Method By introducing a binary relation classification task, we are able to utilize the structure of entity-relation bipartite graph in a more efficient and interpretable way. Experiments on ACE05 show that our model outperforms existing joint models in entity performance and is competitive with the state-of-the-art in relation performance.

Figures and Tables from this paper

Improving Graph Convolutional Networks Based on Relation-Aware Attention for End-to-End Relation Extraction

A novel end-to-end neural model based on graph convolutional networks (GCN) for jointly extracting entities and relations between them and proposes a novel relation-aware attention mechanism to obtain the relation representation between two entity spans.

A Span-based Model for Joint Entity and Relation Extraction with Relational Graphs

  • Xingang WangDong WangFengpo Ji
  • Computer Science
    2020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)
  • 2020
Span-RG is presented, a span-based relation extraction model which uses graph convolutional networks to jointly learn entities and relations and demonstrates that the performance of the model is significantly better than the baseline method.

Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation Extraction

This paper designs a novel synchronous dual network (SDN) with cross-type attention via separately and interactively considering the entity types and relation types and proposes a new multi-task learning strategy via modeling the interaction of two types of information.

Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks

A novel deep learning model to simultaneously solve the four tasks of IE in a single model (called FourIE) that achieves the state-of-the-art performance for joint IE on both monolingual and multilingual learning settings with three different languages.

Joint Entity-Relation Extraction via Improved Graph Attention Networks

This work proposed a novel joint model named extracting Entity-Relations viaImproved Graph Attention networks (ERIGAT), which enhances the ability of the relation extraction task, and improved the graph attention network by designing a new multi-head attention mechanism and sharing attention parameters.

A Relational Adaptive Neural Model for Joint Entity and Relation Extraction

A relational-adaptive entity relation joint extraction model based on multi-head self-attention and densely connected graph convolution network (which is called MA-DCGCN) is proposed in the paper and achieves state-of-the-art performance.

Effective Cascade Dual-Decoder Model for Joint Entity and Relation Extraction

This work proposes an effective cascade dual-decoder approach to extract overlapping relational triples, which includes a text-specific relation decoder and a relation-corresponded entity decoder, which outperforms state-of-the-art methods and achieves better F1 scores under the strict evaluation metric.

Joint Entity and Relation Extraction with Adaptive Thresholding

This paper innovatively design a joint extraction model based on a multi-headed self-attentive mechanism, and also introduces a word-level adaptive threshold to replace the global threshold to help the model extract triples.

A Unified Multi-Task Learning Framework for Joint Extraction of Entities and Relations

A unified multi-task learning framework to divide the joint extraction of entities and relations into three interacted sub-tasks and introduces the type-attentional method for subject extraction to provide prior type information explicitly and a question generation based QA method for object extraction to obtain diverse queries automatically.

Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy

This paper decomposes the joint extraction task into two interrelated subtasks, namely HE extraction and TER extraction, and deconstructed into several sequence labeling problems based on the proposed span-based tagging scheme, which are conveniently solved by a hierarchical boundary tagger and a multi-span decoding algorithm.



Joint Extraction of Entities and Relations Based on a Novel Graph Scheme

This paper converts the joint task into a directed graph by designing a novel graph scheme and proposes a transition-based approach to generate the directed graph incrementally, which can achieve joint learning through joint decoding.

Extracting Entities and Relations with Joint Minimum Risk Training

This work proposes a new lightweight joint learning paradigm based on minimum risk training (MRT) which optimizes a global loss function which is flexible and effective to explore interactions between the entity model and the relation model.

Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme

A novel tagging scheme is proposed that can convert the joint extraction task to a tagging problem, and different end-to-end models are studied to extract entities and their relations directly, without identifying entities and relations separately.

A Walk-based Model on Entity Graphs for Relation Extraction

A novel graph-based neural network model for relation extraction that treats multiple pairs in a sentence simultaneously and considers interactions among them and achieves performance comparable to the state-of-the-art systems on the ACE 2005 dataset without using any external tools.

Incremental Joint Extraction of Entity Mentions and Relations

An incremental joint framework to simultaneously extract entity mentions and relations using structured perceptron with efficient beam-search is presented, which significantly outperforms a strong pipelined baseline, which attains better performance than the best-reported end-to-end system.

Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees

It is shown that attention along with long short term memory (LSTM) network can extract semantic relations between entity mentions without having access to dependency trees.

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction

An extension of graph convolutional networks that is tailored for relation extraction, which pools information over arbitrary dependency structures efficiently in parallel is proposed, and a novel pruning strategy is applied to the input trees by keeping words immediately around the shortest path between the two entities among which a relation might hold.

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

A version of graph convolutional networks (GCNs), a recent class of neural networks operating on graphs, suited to model syntactic dependency graphs, is proposed, observing that GCN layers are complementary to LSTM ones.

End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures

A novel end-to-end neural model to extract entities and relations between them and compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).

Distantly Supervised Entity Relation Extraction with Adapted Manual Annotations

By developing a novel adaptation algorithm, this work is able to transfer the high quality but heterogeneous entity relation annotations in a robust and consistent way to the large automatically generated dataset.