FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

Gao, Tianyu; Han, Xu; Zhu, Hao; Liu, Zhiyuan; Li, Peng; Sun, Maosong; Zhou, Jie

doi:10.18653/v1/d19-1649

Cited by 194 publications

(199 citation statements)

References 12 publications

Supporting

Mentioning

199

Contrasting

Order By: Relevance

“…Han et al [23] investigated few-shot learning for relation extraction and provide a dataset for this specific task. Gao et al [18] improved the former dataset by addressing domain adaptation issues and "none-of-the-above" case which adds extra class to the model. Prototypical networks which assume classification models built on prototypes rather than class labels enable the classifier to identify new classes when only few instances are present for each of those [17,44].…”

Section: Few-shot Instancesmentioning

confidence: 99%

See 1 more Smart Citation

Neural relation extraction: a review

Aydar¹,

Bozal²,

Özbay³

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Neural relation extraction discovers semantic relations between entities from unstructured text using deep learning methods. In this study, we make a clear categorization of the existing relation extraction methods in terms of data expressiveness and data supervision, and present a comprehensive and comparative review. We describe the evaluation methodologies and the datasets used for model assessment. We explicitly state the common challenges in relation extraction task and point out the potential of the pre-trained models to solve them. Accordingly, we investigate additional research directions and improvement ideas in this field.

show abstract

Section: Few-shot Instancesmentioning

confidence: 99%

“…FewRel [18] is a supervised dataset for relation classification methods utilizing few-shot learning approach.…”

Section: Few-shot Instancesmentioning

confidence: 99%

Neural relation extraction: a review

Aydar¹,

Bozal²,

Özbay³

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…For BERT, we use BERT-base as the initialized parameters and the hidden size is 768. Optimizer and other parameters follow [5,6].…”

Section: Training Details and Hyperparametersmentioning

confidence: 99%

Enhance Prototypical Network with Text Descriptions for Few-shot Relation Classification

Yang

Zheng

Dai

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Recently few-shot relation classification has drawn much attention. It devotes to addressing the long-tail relation problem by recognizing the relations from few instances. The existing metric learning methods aim to learn the prototype of classes and make prediction according to distances between query and prototypes. However, it is likely to make unreliable predictions due to the text diversity. It is intuitive that the text descriptions of relation and entity can provide auxiliary support evidence for relation classification. In this paper, we propose TD-Proto, which enhances prototypical network with relation and entity descriptions. We design a collaborative attention module to extract beneficial and instructional information of sentence and entity respectively. A gate mechanism is proposed to fuse both information dynamically so as to obtain a knowledge-aware instance. Experimental results demonstrate that our method achieves excellent performance. CCS CONCEPTS • Computing methodologies → Information extraction.

show abstract

“…1 We also compare with strong baselines with BERT (Devlin et al, 2019) encoders. BERT-PAIR (Gao et al, 2019b) measures the similarity of an instance pair using BERT. In addition, we also implement the enhanced Prototypical Network and MAML (Finn et al, 2017) with BERT encoder for fair comparisons.…”

Section: Experiments Settingsmentioning

confidence: 99%

“…Specifically targeting few-shot relation classification, Gao et al (2019a) introduce a hybrid attention mechanism to alleviate noise data problems. Ye and Ling (2019;Soares et al (2019;Gao et al (2019b;Sui et al (2020) utilize local feature comparison to further improve few-shot performance.…”

Section: Related Workmentioning

confidence: 99%

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification

Dong¹,

Yao²,

Xie³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Few-shot classification requires classifiers to adapt to new classes with only a few training instances. State-of-the-art meta-learning approaches such as MAML learn how to initialize and fast adapt parameters from limited instances, which have shown promising results in few-shot classification. However, existing meta-learning models solely rely on implicit instance-based statistics, and thus suffer from instance unreliability and weak interpretability. To solve this problem, we propose a novel meta-information guided meta-learning (MIML) framework, where semantic concepts of classes provide strong guidance for meta-learning in both initialization and adaptation. In effect, our model can establish connections between instance-based information and semantic-based information, which enables more effective initialization and faster adaptation. Comprehensive experimental results on few-shot relation classification demonstrate the effectiveness of the proposed framework. Notably, MIML achieves comparable or superior performance to humans with only one shot on FewRel evaluation. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/MIML.

show abstract

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

Cited by 194 publications

References 12 publications

Neural relation extraction: a review

Neural relation extraction: a review

Enhance Prototypical Network with Text Descriptions for Few-shot Relation Classification

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification

Contact Info

Product

Resources

About