Papers with Meta-learning

16 papers
Meta Learning and Its Applications to Natural Language Processing (2021.acl-tutorials)

Copied to clipboard

Challenge: Meta-learning is a new technique that aims to learn better learning algorithms, including better parameter initialization, optimization strategy, network architecture, distance metrics, and beyond.
Approach: This tutorial introduces Meta-learning approaches and the theory behind them, and then reviews the works of applying this technology to NLP problems.
Outcome: This tutorial will introduce Meta-learning approaches and the theory behind them, and then review the works of applying this technology to NLP problems.
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.
Meta Learning for Natural Language Processing: A Survey (2022.naacl-main)

Copied to clipboard

Challenge: Meta-learning is an emerging field in machine learning, but there is no systematic survey of these approaches in NLP.
Approach: They propose to introduce meta-learning and the common approaches and summarize their work and review their work in the NLP community.
Outcome: The proposed methods improve performance in many NLP tasks but are limited to domains, languages, countries, or styles.
DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference (2021.naacl-main)

Copied to clipboard

Challenge: Meta-learning has not yet succeeded in NLP due to the lack of a well-defined task distribution . meta-learners tend to overfit their adaptation mechanism and datasets are heterogeneous .
Approach: They propose a method for decomposing datasets into Reasoning Categories to form additional high quality tasks.
Outcome: The proposed method improves the accuracy of meta-learners by 1.5-4% across four few-shot NLI problems.
Knowledge-Aware Meta-learning for Low-Resource Text Classification (2021.emnlp-main)

Copied to clipboard

Challenge: Existing meta-learning techniques may not be well-suited to testing tasks when they are not well-supported by training tasks.
Approach: They propose to use a meta-learning algorithm to add representations for each sentence learned from the extracted sentence-specific knowledge graph.
Outcome: The proposed model is able to represent each sentence learned from the extracted knowledge graph under supervised adaptation and unsupervised adaptation settings.
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches for few-shot text classification rely on exploitation of lexical features and distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks.
Approach: They propose a meta-learning framework integrated with an adversarial domain adaptation network to improve the model's adaptive ability and generate high-quality text embedding for new classes.
Outcome: The proposed framework outperforms the state-of-the-art models on four datasets and shows clear superiority over existing models.
MetaMixSpeech: Meta Task Augmentation for Low-Resource Speech Recognition (2025.findings-emnlp)

Copied to clipboard

Challenge: Meta-learning has proven to be a powerful paradigm for improving speech recognition performance . however, multilingual meta learning also faces challenges such as task overfitting and learner overfit .
Approach: a new method is proposed to augment meta-training tasks with "more data" the method incorporates both support and query augmentations .
Outcome: The proposed method achieves a 6.35% improvement in the word error rate on FLEURS and Common Voice datasets.
Exploring Task Difficulty for Few-Shot Relation Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models do not distinguish hard tasks from easy ones in the learning process.
Approach: They propose a novel approach that exploits relation label information to learn better representations by focusing on hard tasks.
Outcome: Experiments on two standard datasets show the proposed approach performs better than previous methods.
Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for word sense disambiguation (WSD) are limited and require large datasets annotated with word senses.
Approach: They propose a meta-learning framework for few-shot word sense disambiguation where the goal is to learn to disambiguate unseen words from only a few labeled instances.
Outcome: The proposed framework is based on a large training dataset and a small number of examples.
Classical Sequence Match Is a Competitive Few-Shot One-Class Learner (2022.coling-1)

Copied to clipboard

Challenge: Existing models that use transformers are unable to learn new knowledge in the few-shot scenarios.
Approach: They propose a few-shot one-class problem which takes a known sample as a reference to detect whether an unknown instance belongs to the same class.
Outcome: The proposed method significantly outperforms transformer models under meta-learning and fine-tuning.
Sentence-aware Adversarial Meta-Learning for Few-Shot Text Classification (2022.coling-1)

Copied to clipboard

Challenge: Existing studies fail to consider the importance of the semantic interaction between sentence features and neglect to enhance the generalization ability of the model to new tasks.
Approach: They propose to integrate an adversarial network architecture into the meta-learning system and leverage cost-effective modules to build a few-shot classification framework called SaAML.
Outcome: The proposed framework outperforms state-of-the-art methods on four benchmark datasets.
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP (2021.emnlp-main)

Copied to clipboard

Challenge: Meta-learning considers learning as an efficient learning process that can leverage its past experience to accurately solve new tasks.
Approach: They propose to provide task distributions for meta-learning by considering self-supervised tasks automatically proposed from unlabeled text to enable large-scale meta- learning in NLP.
Outcome: The proposed distributions show that human learning models perform better on the few-shot benchmark than previous methods.
Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing (2022.acl-long)

Copied to clipboard

Challenge: Meta-learning can help overcome resource scarcity in cross-lingual NLP problems . pre-training of models requires large annotated training sets for the task at hand .
Approach: They propose to use meta-learning to train a model to learn a parameter initialization that can adapt quickly to new languages.
Outcome: The proposed model-agnostic meta-learning improves on language transfer and standard supervised learning baselines for unseen, typologically diverse, and low-resource languages in a few-shot learning setup.
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for fewshot text classification depend on inter-class variance . Existing approaches suffer from MLADA, which performs poorly on tasks with high inter- class variance whereas it fails to distinguish samples from tasks with low inter-group variance.
Approach: They propose a task-adaptive reference transformation network to transform class prototypes to per-class fixed reference points in task-adapted metric spaces.
Outcome: The proposed method surpasses state-of-the-art methods in 1-shot and 5-shot classifications on the 20 Newsgroups dataset.
Meta-Learning Neural Mechanisms rather than Bayesian Priors (2025.acl-long)

Copied to clipboard

Challenge: a meta-learning approach has been proposed to integrate human-like learning biases into neural networks . a recent study suggests that meta-training on a single formal language can improve a model .
Approach: They propose to integrate human-like learning biases into neural-network architectures . they use symbolic models to capture aspects of humans' basic generalisations from small data .
Outcome: The proposed model can learn from a single language as much as 5000 different languages . the model can be scaled to a larger model and training datasets .
Detecting Sockpuppetry on Wikipedia Using Meta-Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to model author-specific sockpuppet detection on Wikipedia are limited in data-scarce settings.
Approach: They propose to use meta-learning to improve model adaptation to a new sockpuppet-group by training models across multiple tasks.
Outcome: The proposed technique improves performance in data-scarce settings by training models across multiple tasks.

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