Challenge: Existing methods to solve label dependency and noisy labeling problems are limited . experimental results show the proposed method is competitive to state-of-the-art methods .
Approach: They propose a deep learning XML method with word-vector-based self-attention followed by ranking-based AutoEncoder architecture to solve these problems.
Outcome: The proposed method is competitive to state-of-the-art methods on benchmark datasets.

Similar Papers

Enhancing Extreme Multi-Label Text Classification: Addressing Challenges in Model, Data, and Evaluation (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to extreme multi-label text classification face inherent challenges in terms of model, data, and evaluation.
Approach: They propose a label ranking model as an alternative to the conventional SciBERT-based classification model and an active learning-based pipeline that addresses the data scarcity of new labels during the update of a classification system.
Outcome: The proposed model enables efficient handling of large-scale labels and accommodates new labels.
A Submodular Feature-Aware Framework for Label Subset Selection in Extreme Classification Problems (N19-1)

Copied to clipboard

Challenge: Experimental results show that extreme multi-label learning improves label prediction quality by 3% to 5% in three of the 5 tasks and is competitive in the others.
Approach: They propose a submodular maximization framework with linear cost to find informative labels which are most relevant to other labels yet least redundant with each other.
Outcome: The proposed model improves label prediction quality by 3% to 5% in three of the 5 tasks and is competitive in the others.
Investigating Active Learning Sampling Strategies for Extreme Multi Label Text Classification (2022.lrec-1)

Copied to clipboard

Challenge: Large scale, multi-label text datasets with high numbers of different classes are expensive to annotate due to domain experts taking a lot of time working through all the classes.
Approach: They propose to build classifiers on multi-label text datasets using Active Learning to reduce labeling effort.
Outcome: The proposed classifiers can be used to reduce labeling effort on multi-label datasets.
Cluster-Guided Label Generation in Extreme Multi-Label Classification (2023.eacl-main)

Copied to clipboard

Challenge: Existing classification-based models are poorly per-form for tail labels and ignore semantic relations among labels.
Approach: They propose to guide label generation using label cluster information to hierarchically generate lower-level labels.
Outcome: The proposed model outperforms classification and generation baselines on tail labels and improves in four popular XMC benchmarks.
Prototypical Extreme Multi-label Classification with a Dynamic Margin Loss (2025.naacl-long)

Copied to clipboard

Challenge: Recent work in XMC addresses this problem using deep encoders that project text descriptions to an embedding space suitable for recovering the closest labels.
Approach: They propose a method that uses a shallow transformer encoder to combine text-based embeddings, label centroids and learnable free vectors to improve XMC efficiency.
Outcome: The proposed method achieves state-of-the-art in several public benchmarks of different sizes and domains while keeping the model efficient.
XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach: They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome: The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.
Label-Specific Document Representation for Multi-Label Text Classification (D19-1)

Copied to clipboard

Challenge: Existing methods to classify documents using labels only assign one label to document . multi-label text classification is a challenging task because of the huge amount of documents, words and labels.
Approach: They propose a Label-Specific Attention Network (LSAN) to learn a label-specific document representation.
Outcome: The proposed model outperforms state-of-the-art methods on four datasets . it can predict low-frequency labels, and it can be used in sentimental analysis .
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.
Evaluating Extreme Hierarchical Multi-label Classification (2022.acl-long)

Copied to clipboard

Challenge: Several natural language processing tasks are defined as a classification problem in its most complex form: Multi-label Hierarchical Extreme classification.
Approach: They propose a classification metric inspired by the Information Contrast Model (ICM) they use a set of formal properties to analyze the evaluation metrics.
Outcome: The proposed evaluation metrics are suitable for multi-label hierarchical extreme classification scenarios.
ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification (2024.findings-naacl)

Copied to clipboard

Challenge: Existing research has focused on fully supervised XMC, but real-world scenarios often lack supervision signals, highlighting the importance of zero-shot settings.
Approach: They propose a framework that generates a set of candidate labels through in-context learning and then reranks them.
Outcome: The proposed framework advances state-of-the-art on two diverse public benchmarks.

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