Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
arXiv:2103.16929 · doi:10.1007/s12559-021-09917-7
Abstract
Recently, with the advances made in continuous representation of words (word embeddings) and deep neural architectures, many research works are published in the area of relation extraction and it is very difficult to keep track of so many papers. To help future research, we present a comprehensive review of the recently published research works in relation extraction. We mostly focus on relation extraction using deep neural networks which have achieved state-of-the-art performance on publicly available datasets. In this survey, we cover sentence-level relation extraction to document-level relation extraction, pipeline-based approaches to joint extraction approaches, annotated datasets to distantly supervised datasets along with few very recent research directions such as zero-shot or few-shot relation extraction, noise mitigation in distantly supervised datasets. Regarding neural architectures, we cover convolutional models, recurrent network models, attention network models, and graph convolutional models in this survey.
A survey paper for relation extraction. Cogn Comput (2021)
References in corpus (35)
- Distributed Representations of Words and Phrases and their Compositionality
- Semi-Supervised Classification with Graph Convolutional Networks
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Bidirectional Attention Flow for Machine Comprehension
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Joint entity recognition and relation extraction as a multi-head selection problem
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
- Cross-Sentence N-ary Relation Extraction with Graph LSTMs
- Fine-tune Bert for DocRED with Two-step Process
- Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
- Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention
- Attention Guided Graph Convolutional Networks for Relation Extraction
- Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
- Relation Extraction : A Survey
- A Survey of Deep Learning Methods for Relation Extraction
- End-to-end neural relation extraction using deep biaffine attention
- A Dependency-Based Neural Network for Relation Classification
- Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy
- Entity-Relation Extraction as Multi-Turn Question Answering
- Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning
- DocRED: A Large-Scale Document-Level Relation Extraction Dataset
- More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
- Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
- Contrastive Triple Extraction with Generative Transformer
- A Silver Standard Corpus of Human Phenotype-Gene Relations
- DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
- RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
- Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
- Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions
- N-ary Relation Extraction using Graph State LSTM
- Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
- A hybrid deep learning approach for medical relation extraction
- Leveraging Dependency Forest for Neural Medical Relation Extraction
- Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations
- Deep Neural Networks for Relation Extraction