A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction
Tianyu Liu,Kexiang Wang,Baobao Chang,Zhifang Sui +3 more
- pp 1790-1795
TLDR
This work introduces an entity-pair level denoise method which exploits semantic information from correctly labeled entity pairs to correct wrong labels dynamically during training, and proposes a joint score function which combines the relational scores based on the entity- Pair representation and the confidence of the hard label to obtain a new label.Abstract:
Distant-supervised relation extraction inevitably suffers from wrong labeling problems because it heuristically labels relational facts with knowledge bases. Previous sentence level denoise models don’t achieve satisfying performances because they use hard labels which are determined by distant supervision and immutable during training. To this end, we introduce an entity-pair level denoise method which exploits semantic information from correctly labeled entity pairs to correct wrong labels dynamically during training. We propose a joint score function which combines the relational scores based on the entity-pair representation and the confidence of the hard label to obtain a new label, namely a soft label, for certain entity pair. During training, soft labels instead of hard labels serve as gold labels. Experiments on the benchmark dataset show that our method dramatically reduces noisy instances and outperforms other state-of-the-art systems.read more
Citations
More filters
Posted Content
Learning from Noisy Labels with Deep Neural Networks: A Survey
TL;DR: A comprehensive review of 62 state-of-the-art robust training methods, all of which are categorized into five groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority.
Posted Content
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
TL;DR: This paper presented a few-shot relation classification dataset (FewRel) consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. And they adapted the most recent state-of-the-art fewshot learning methods for relation classification and conduct a thorough evaluation of these methods.
Proceedings ArticleDOI
FewRel: A Large-Scale Supervised Few-shot Relation Classification Dataset with State-of-the-Art Evaluation.
TL;DR: This paper presented a few-shot relation classification dataset, consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers, where the relation of each sentence is first recognized by distant supervision methods, and then filtered by crowd workers.
Journal ArticleDOI
Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification
TL;DR: This paper designs instancelevel and feature-level attention schemes based on prototypical networks to highlight the crucial instances and features respectively, which significantly enhances the performance and robustness of RC models in a noisy FSL scenario.
Posted Content
Reinforcement Learning for Relation Classification from Noisy Data
TL;DR: The authors proposed a novel model for relation classification at the sentence level from noisy data, where an instance selector chooses high-quality sentences with reinforcement learning and feeds the selected sentences into the relation classifier, which makes sentence level prediction and provides rewards to the instance selector.
References
More filters
Proceedings ArticleDOI
Freebase: a collaboratively created graph database for structuring human knowledge
TL;DR: MQL provides an easy-to-use object-oriented interface to the tuple data in Freebase and is designed to facilitate the creation of collaborative, Web-based data-oriented applications.
Proceedings ArticleDOI
Distant supervision for relation extraction without labeled data
TL;DR: This work investigates an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size.
Proceedings Article
Relation Classification via Convolutional Deep Neural Network
TL;DR: This paper exploits a convolutional deep neural network (DNN) to extract lexical and sentence level features from the output of pre-existing natural language processing systems and significantly outperforms the state-of-the-art methods.
Book ChapterDOI
Modeling relations and their mentions without labeled text
TL;DR: A novel approach to distant supervision that can alleviate the problem of noisy patterns that hurt precision by using a factor graph and applying constraint-driven semi-supervision to train this model without any knowledge about which sentences express the relations in the authors' training KB.
Proceedings ArticleDOI
Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks
TL;DR: This paper proposes a novel model dubbed the Piecewise Convolutional Neural Networks (PCNNs) with multi-instance learning to address the problem of wrong label problem when using distant supervision for relation extraction and adopts convolutional architecture with piecewise max pooling to automatically learn relevant features.