Knowledge Guided Metric Learning for Few-Shot Text Classification

Sui, Dianbo; Chen, Yubo; Mao, Binjie; Qiu, Delai; Liu, Kang; Zhao, Jun

doi:10.48550/arxiv.2004.01907

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The information-injected knowledge-assisted LSL method is mainly dedicated to designing a coupling strategy of knowledge modules and conventional feature modules. [181,205] models knowledge independent to conventional text modeling pipeline and combines knowledge features with standard language model features to be used together for metric-based FSL text classification. In [29,130,168], in order to optimize the consistency of standard features and knowledge features, before integrating knowledge information and standard features, the model utilizes an auxiliary loss function to optimize the correlation between them.…”

Section: Leveraging Structured Data For Lslmentioning

confidence: 99%

See 1 more Smart Citation

What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data

Hu¹,

Chapman²,

Wen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Supervised machine learning has several drawbacks that make it difficult to use in many situations. Drawbacks include: heavy reliance on massive training data, limited generalizability and poor expressiveness of high-level semantics. Low-shot Learning attempts to address these drawbacks. Low-shot learning allows the model to obtain good predictive power with very little or no training data, where structured knowledge plays a key role as a high-level semantic representation of human. This article will review the fundamental factors of low-shot learning technologies, with a focus on the operation of structured knowledge under different low-shot conditions. We also introduce other techniques relevant to low-shot learning. Finally, we point out the limitations of low-shot learning, the prospects and gaps of industrial applications, and future research directions.

show abstract

Section: Leveraging Structured Data For Lslmentioning

confidence: 99%

“…II. Model Training Many LSL methods use auxiliary knowledge systems to provide help creating teh model [11,19,102,113,129,151,205,224,228,259,280]. For structured data modeling, this idea is more generally embodied as "using knowledge to learn knowledge [40,100,153,183,275]. "…”

Section: Identified Challengesmentioning

confidence: 99%

What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data

Hu¹,

Chapman²,

Wen³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

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

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

Meta-learning for Few-shot Natural Language Processing: A Survey

Yin¹

2020

Preprint

View full text Add to dashboard Cite

Knowledge Guided Metric Learning for Few-Shot Text Classification

Cited by 3 publications

References 9 publications

What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data

What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data

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

Meta-learning for Few-shot Natural Language Processing: A Survey

Contact Info

Product

Resources

About