Open Set Relation Extraction via Unknown-Aware Training

• URL: http://arxiv.org/abs/2306.04950v1
• Date: Thu, 8 Jun 2023 05:45:25 GMT
• Title: Open Set Relation Extraction via Unknown-Aware Training
• Authors: Jun Zhao, Xin Zhao, Wenyu Zhan, Qi Zhang, Tao Gui, Zhongyu Wei, Yunwen Chen, Xiang Gao, Xuanjing Huang
• Abstract summary: We propose an unknown-aware training method, regularizing the model by dynamically synthesizing negative instances. Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances. Experimental results show that this method achieves SOTA unknown relation detection without compromising the classification of known relations.
• Score: 72.10462476890784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The existing supervised relation extraction methods have achieved impressive performance in a closed-set setting, where the relations during both training and testing remain the same. In a more realistic open-set setting, unknown relations may appear in the test set. Due to the lack of supervision signals from unknown relations, a well-performing closed-set relation extractor can still confidently misclassify them into known relations. In this paper, we propose an unknown-aware training method, regularizing the model by dynamically synthesizing negative instances. To facilitate a compact decision boundary, ``difficult'' negative instances are necessary. Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations. Experimental results show that this method achieves SOTA unknown relation detection without compromising the classification of known relations.

Related papers

• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Improving Continual Relation Extraction by Distinguishing Analogous Semantics [11.420578494453343]
  Continual relation extraction aims to learn constantly emerging relations while avoiding forgetting the learned relations. Existing works store a small number of typical samples to re-train the model for alleviating forgetting. We conduct an empirical study on existing works and observe that their performance is severely affected by analogous relations.
  arXiv  Detail & Related papers  (2023-05-11T07:32:20Z)
• Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data [36.54640096189285]
  bootstrap learning is motivated by the intuition that the higher uncertainty of an instance, the more likely the model confidence is inconsistent with the ground truths. We first explore instance-level data uncertainty to create an initial high-confident examples. During bootstrap learning, we propose self-ensembling as a regularizer to alleviate inter-model uncertainty produced by noisy labels.
  arXiv  Detail & Related papers  (2023-05-05T20:06:11Z)
• HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction [60.80849503639896]
  Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution. We propose a novel contrastive learning framework named HiURE, which has the capability to derive hierarchical signals from relational feature space using cross hierarchy attention. Experimental results on two public datasets demonstrate the advanced effectiveness and robustness of HiURE on unsupervised relation extraction when compared with state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-04T17:56:48Z)
• Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction [8.764365529317923]
  We propose a two-stage approach to false negative relation extraction. First, it finds out possible FN samples by leveraging the memory mechanism of deep neural networks. Then, it aligns those unlabeled data with the training data into a unified feature space by adversarial training to assign pseudo labels.
  arXiv  Detail & Related papers  (2021-09-05T15:11:24Z)
• ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning [10.609715843964263]
  We formulate the zero-shot relation extraction problem by incorporating the text description of seen and unseen relations. We propose a novel multi-task learning model, zero-shot BERT, to directly predict unseen relations without hand-crafted labeling and multiple pairwise attribute classifications. Experiments conducted on two well-known datasets exhibit that ZS-BERT can outperform existing methods by at least 13.54% improvement on F1 score.
  arXiv  Detail & Related papers  (2021-04-10T06:53:41Z)
• Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training [49.9995628166064]
  We propose CTEG, a model equipped with two mechanisms to learn to decouple easily-confused relations. On the one hand, an EGA mechanism is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations.
  arXiv  Detail & Related papers  (2020-10-21T11:07:53Z)
• Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents [52.55119217982361]
  We propose a joint extraction approach to handle noisy instances with a group of cooperative multiagents. To handle noisy instances in a fine-grained manner, each agent in the cooperative group evaluates the instance by calculating a continuous confidence score from its own perspective. A confidence consensus module is designed to gather the wisdom of all agents and re-distribute the noisy training set with confidence-scored labels.
  arXiv  Detail & Related papers  (2020-04-21T12:03:04Z)
• Discovering Nonlinear Relations with Minimum Predictive Information Regularization [67.7764810514585]
  We introduce a novel minimum predictive information regularization method to infer directional relations from time series. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets.
  arXiv  Detail & Related papers  (2020-01-07T04:28:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.