Papers with supervised relation extraction
Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Distantly supervised relation extraction is used in knowledge bases but its low quality and noisy sentences are present in sentence bags. |
| Approach: | They propose a multi-layer revision network which emphasizes inner-sentence correlations before extracting relevant information within sentences. |
| Outcome: | The proposed method improves on two New York Times datasets. |
Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)
Copied to clipboard
| Challenge: | Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance. |
| Approach: | They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning. |
| Outcome: | The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods. |
Bootstrapping Relation Extractors using Syntactic Search by Examples (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for supervised relation extraction still require a large quantity of training data. |
| Approach: | They propose a process for bootstrapping training datasets which can be performed quickly by non-NLP-experts. |
| Outcome: | The proposed method outperforms models trained on manual and distant data augmentation techniques and the search-based approach with the NLG method. |
Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction (P19-1)
Copied to clipboard
| Challenge: | Current relation extraction methods suffer from noisy labels and incomplete knowledge base information. |
| Approach: | They propose a pre-trained language model that captures semantic and syntactic features and a significant amount of “common-sense” knowledge. |
| Outcome: | The proposed model achieves state-of-the-art AUC score of 0.422 on the NYT10 dataset and performs especially well at higher recall levels. |
CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use noisy instances and poor quality training data. |
| Approach: | They propose a sentence-level DSRE method that denies noisy samples from the wrong classification space on the feature space by enhancing the classification consensus between two discrepant classifiers. |
| Outcome: | The proposed method outperforms existing methods on widely-used benchmarks and significantly outperformed existing methods. |
A Simple Model for Distantly Supervised Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Recent methods focus on exploiting bag representations with complex de-noising scheme to achieve remarkable performance. |
| Approach: | They propose a BERT-based Graph convolutional network model that exploits bag representations . their model extracts key information from each instance and constructs a bag graph . |
| Outcome: | The proposed model improves on two benchmark datasets, i.e., NYT10 and GDS. |
Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention (D18-1)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use knowledge graphs to automatically label training data . but, it suffers from the wrong labeling problem because not all sentences containing two entities can express their relations in KGs . |
| Approach: | They propose a distant supervision approach to automatically label training instances . they integrate hierarchical information of relations into distantly supervised relation extraction . |
| Outcome: | The proposed model outperforms baseline models on a large-scale dataset. |
Structured Minimally Supervised Learning for Neural Relation Extraction (N19-1)
Copied to clipboard
| Challenge: | Recent work shows that distant supervision can cause significant label noise when learning from large quantities of unlabeled text. |
| Approach: | They propose a method that combines the benefits of learning representations and structured learning to predict sentence-level relation mentions given only proposition-level supervision from a KB. |
| Outcome: | The proposed approach outperforms a number of baseline approaches while minimizing label noise. |
Regularized Attentive Capsule Network for Overlapped Relation Extraction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to extract relations from distant supervision contain low-quality instances with noisy words and overlapped relations. |
| Approach: | They propose a Regularized Attentive Capsule Network to better identify overlapped relations in informal sentences . they embed multi-head attention into the capsule network as the low-level capsules . |
| Outcome: | Extensive experiments show that the proposed model improves relation extraction. |
Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction ignore the incompleteness of existing knowledge bases . current methods are too weak and cause noises when training and testing are not based on training data. |
| Approach: | They propose a method to automatically align unstructured text with relation instances in a knowledge base . they use heuristics to leverage the memory mechanism of deep neural networks to find out possible FN samples . |
| Outcome: | Experiments on two wildly-used benchmark datasets show the effectiveness of the proposed method. |
Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation Extraction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Distantly supervised relation extraction (DSRE) methods are not capable of extracting relation labels for individual sentences. |
| Approach: | They propose a semi-supervised learning relation extraction framework for sentence-level DSRE . they discard only the labels of the noisy samples and utilize them as unlabeled samples . |
| Outcome: | The proposed framework achieves significant performance enhancements on two real-world datasets. |