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
Ilias Chalkidis, Manos Fergadiotis, Sotiris Kotitsas, Prodromos Malakasiotis, Nikolaos Aletras, Ion Androutsopoulos
| 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. |