text-classification
960 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in text-classification
Libraries
Use these libraries to find text-classification models and implementationsMost implemented papers
Augmenting Interpretable Models with LLMs during Training
csinva/imodelsX
•
•
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks.
HDLTex: Hierarchical Deep Learning for Text Classification
kk7nc/HDLTex
•
•
This is because along with this growth in the number of documents has come an increase in the number of categories.
BERTweet: A pre-trained language model for English Tweets
VinAIResearch/BERTweet
•
•
EMNLP 2020
We present BERTweet, the first public large-scale pre-trained language model for English Tweets.
Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers
To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations.
X-Class: Text Classification with Extremely Weak Supervision
ZihanWangKi/XClass
•
•
NAACL 2021
Finally, we pick the most confident documents from each cluster to train a text classifier.
Transformer Interpretability Beyond Attention Visualization
hila-chefer/Transformer-Explainability
•
•
CVPR 2021
Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks.
Generating Natural Language Attacks in a Hard Label Black Box Setting
RishabhMaheshwary/hard-label-attack
•
•
Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model.
Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e. g., by computing validation error rate) or leverages statistic-based methods (e. g. median and Krum) to identify and remove malicious gradients from Byzantine clients.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
HKUNLP/zerogen
•
•
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs).
Correlation Networks for Extreme Multi-label Text Classification
XunGuangxu/CorNet
•
•
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2022
This paper develops the Correlation Networks (CorNet) architecture for the extreme multi-label text classification (XMTC) task, where the objective is to tag an input text sequence with the most relevant subset of labels from an extremely large label set.
