Few-Shot Learning for Cold-Start Recommendation (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for cold-start learning and recommendation are brittle to scenarios with few interactions.
Approach: They propose a Few-shot learning method for Cold-Start recommendation that consists of three hierarchical structures that are local and global .
Outcome: The proposed method improves on two public real-world datasets and is stable compared with the state-of-the-art.

Similar Papers

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification (2020.coling-main)

Copied to clipboard

Challenge: Existing meta-learning models rely on implicit instance statistics and are unreliability and weak interpretability.
Approach: They propose a meta-information guided meta-learning framework that uses semantics to guide meta- learning . experimental results demonstrate the effectiveness of the proposed framework .
Outcome: The proposed framework can establish connections between instance-based information and semantic-based data, enabling faster initialization and adaptation.
Making Pre-trained Language Models Better Few-shot Learners (2021.acl-long)

Copied to clipboard

Challenge: Recent studies show that the GPT-3 model can perform few-shots on language understanding tasks with a natural-language prompt and a few task demonstrations.
Approach: They propose a technique for fine-tuning language models using a few examples . they propose LM-BFF, which uses prompt-based fine-uning and a pipeline for automating prompt generation .
Outcome: The proposed approach outperforms standard fine-tuning procedures on a range of NLP tasks.
Prompt-Based Meta-Learning For Few-shot Text Classification (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to learn text labels require large amounts of data to build many few-shot tasks.
Approach: They propose a Prompt-Based Meta-Learning model that adds the prompting mechanism to the meta-learning method.
Outcome: The proposed method improves on four text classification datasets with high accuracy and robustness.
Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for prompt tuning can overfit to few-shot training samples, causing overfitting . authors propose a new framework for prompt learning with supervised meta-learning .
Approach: They propose a self-supervised meta-prompt learning framework with MEta-gradient Regularization for few-shot generalization that leverages self-recognized meta-learning with a diverse set of meta-tasks to learn a universal prompt initialization using only unlabeled data.
Outcome: The proposed framework learns a universal prompt initialization for efficient adaptation using only unlabeled data.
Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for few-shot text classification often encounter problems drawing accurate class prototypes from support set samples.
Approach: They propose a meta-learning method that leverages the information within the task itself . they propose Query-Data-Augmenter and Label-Adapter to build a task-adaptive metric space .
Outcome: The proposed method shows obvious advantages over state-of-the-art models on eight benchmark datasets.
Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models (2022.findings-acl)

Copied to clipboard

Challenge: Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning.
Approach: They propose to fine tune masked language models with training examples and task descriptions to reduce prompt engineering by using null prompts.
Outcome: The proposed prompts can be used to improve few-shot learning by finetuning only the bias terms while updating only 0.1% of the parameters.
Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for few-shot relation extraction are not realistic due to the large amount of training data required.
Approach: They propose a meta dataset for few-shot relation extraction based on existing supervised relation extraction datasets and a few-shot form of the TACRED dataset.
Outcome: The proposed methods perform poorly on the few-shot relation extraction task.
Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes (2021.tacl-1)

Copied to clipboard

Challenge: a recent study has focused on few-shot learning (FSL) for relation classification, but it requires large amounts of training data.
Approach: They propose a method for deriving more realistic few-shot test data from available datasets for supervised RC.
Outcome: The proposed method yields a challenging benchmark for FSL-RC on which state of the art models show poor performance.
Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task.
Approach: They propose to use few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts.
Outcome: The proposed method outperforms the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task.
Towards Realistic Few-Shot Relation Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that few-shot relation classification models can be used to extract any relation of interest from a collection of text with only a few example instances.
Approach: They propose to modify the training routine to encourage models to better discriminate between relations involving similar entity types.
Outcome: The proposed models outperform human models on relation extraction tasks while relying on entity type information.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations