Computationally Efficient Wasserstein Loss for Structured Labels (2021.eacl-srw)

Copied to clipboard

Challenge: Existing approaches to estimate the probability distribution of labels are based on tree-Wasserstein distance.
Approach: They propose a tree-Wasserstein distance regularized LDL algorithm for hierarchical text classification tasks.
Outcome: The proposed method performs well on synthetic and real-world datasets and compares favorably with the Sinkhorn algorithm in terms of computation time and memory usage.

Similar Papers

Random Label Forests: An Ensemble Method with Label Subsampling For Extreme Multi-Label Problems (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for multi-label learning require large memory space for text classification . recent studies show that multiple labels are needed for e-commerce applications .
Approach: They propose a distributed ensemble method with label subsampling to share large memory space for handling large-scale labels.
Outcome: The proposed method can reduce memory usage while keeping competitive performance over real-world data sets.
Hierarchical Label Generation for Text Classification (2023.findings-eacl)

Copied to clipboard

Challenge: None Hierarchical text classification (HTC) aims to assign the most relevant labels with their structure for a given document.
Approach: They propose a method that captures the label hierarchy for real-world classification applications by using a taxonomic hierarchy.
Outcome: The proposed method can generate unseen labels in subword level.
Learning Label Hierarchy with Supervised Contrastive Learning (2024.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to supervised contrastive learning treat each class as independent and therefore consider all classes to be equally important.
Approach: They propose a family of Label-Aware SCL methods that incorporate hierarchical information to SCL by leveraging similarities between classes.
Outcome: The proposed method outperforms baseline supervised approaches on three datasets.
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification (2021.acl-long)

Copied to clipboard

Challenge: Existing methods ignore the semantic relationship between text and labels, so they cannot make full use of hierarchical information.
Approach: They propose a hierarchy-aware label semantics matching network to model the semantic relationship between text and labels in a semantic matching problem.
Outcome: The proposed model captures the text-label semantics matching relationship among coarse-grained labels and fine-grain labels in a hierarchy-aware manner.
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for regularizing deep neural networks rely on weight decay, dropout, batch/layer normalization to converge faster and generalize.
Approach: They propose a framework for training with label regularization which includes conventional LS but can also model instance-specific variants.
Outcome: The proposed approach consistently yields better results than conventional regularization on seven machine translation and three image classification tasks while maintaining training efficiency.
Learning under Label Proportions for Text Classification (2023.findings-emnlp)

Copied to clipboard

Challenge: Using a set of data samples with ground truth labels, learning from label proportions is infeasible in many cases.
Approach: They propose a setup where the data is provided in an aggregate form called bags and only the proportion of samples belonging to each class as the ground truth.
Outcome: The proposed model achieves better results than baselines in almost 87% of the configurations.
An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels (2020.emnlp-main)

Copied to clipboard

Challenge: Large-scale Multi-label Text Classification (LMTC) is a type of classification that assigns labels to a large set of labels.
Approach: They propose to use probabilistic label trees to improve frequent, few and zero-shot learning . they propose to combine a new state-of-the-art method with pre-trained Transformers .
Outcome: The proposed models outperform existing models on frequent, few and zero-shot learning on three datasets from different domains.
Transfer Learning Between Related Tasks Using Expected Label Proportions (D19-1)

Copied to clipboard

Challenge: Existing methods of data supervision are limited by labeled training data.
Approach: They propose a method where models are trained based on expected label proportions.
Outcome: The proposed method improves on a sentence-level sentiment predictor and is cumulative with LM-based pretraining.
Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification (2022.acl-short)

Copied to clipboard

Challenge: Existing methods for multi-label text classification neglect the knowledge from the existing similar instances when predicting labels of a specific text.
Approach: They propose a k nearest neighbor mechanism which retrieves several neighbor instances and interpolates the model output with their labels.
Outcome: Extensive experiments show that the proposed method can bring significant performance improvements to multiple MLTC models including state-of-the-art pretrained and non-pretrained ones.
Hierarchically-Refined Label Attention Network for Sequence Labeling (D19-1)

Copied to clipboard

Challenge: Conditional random fields (CRF) is a powerful model for statistical sequence labeling, but it does not give much information gain over strong neural encoding.
Approach: They propose a hierarchically-refined label attention network which captures potential long-term label dependency by giving each word incrementally refined label distributions with hierarchical attention.
Outcome: The proposed model improves POS tagging accuracy and speeds up training and testing compared to the current model.

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